diff --git a/docs/Project.toml b/docs/Project.toml
index 994ec2ee4..9d6f2f299 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -29,6 +29,7 @@ SciMLBase = "0bca4576-84f4-4d90-8ffe-ffa030f20462"
 SciMLSensitivity = "1ed8b502-d754-442c-8d5d-10ac956f44a1"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StochasticDiffEq = "789caeaf-c7a9-5a7d-9973-96adeb23e2a0"
+Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"
 
 [compat]
 CSV = "0.10"
@@ -58,3 +59,4 @@ ReverseDiff = "1.14"
 SciMLBase = "1.72"
 SciMLSensitivity = "7.11"
 StochasticDiffEq = "6.56"
+Zygote = "0.6.62"
\ No newline at end of file
diff --git a/docs/src/examples/hamiltonian_nn.md b/docs/src/examples/hamiltonian_nn.md
index d49a6a370..1e3d372d6 100644
--- a/docs/src/examples/hamiltonian_nn.md
+++ b/docs/src/examples/hamiltonian_nn.md
@@ -63,7 +63,7 @@ ylabel!("Momentum (p)")
 The HNN predicts the gradients ``(\dot q, \dot p)`` given ``(q, p)``. Hence, we generate the pairs ``(q, p)`` using the equations given at the top. Additionally, to supervise the training, we also generate the gradients. Next, we use Flux DataLoader for automatically batching our dataset.
 
 ```@example hamiltonian
-using Flux, DiffEqFlux, DifferentialEquations, Statistics, Plots, ReverseDiff
+using Flux, DiffEqFlux, DifferentialEquations, Statistics, Plots, ReverseDiff, Random, IterTools, Lux, ComponentArrays, Optimization
 
 t = range(0.0f0, 1.0f0, length = 1024)
 π_32 = Float32(π)
diff --git a/docs/src/examples/neural_sde.md b/docs/src/examples/neural_sde.md
index e70252c37..b507ff389 100644
--- a/docs/src/examples/neural_sde.md
+++ b/docs/src/examples/neural_sde.md
@@ -81,7 +81,8 @@ diffusion_dudt = Flux.Chain(Flux.Dense(2, 2))
 p2, re2 = Flux.destructure(diffusion_dudt)
 
 neuralsde = NeuralDSDE(drift_dudt, diffusion_dudt, tspan, SOSRI(),
-                       saveat = tsteps, reltol = 1e-1, abstol = 1e-1)
+                       saveat = tsteps, reltol = 1e-1, abstol = 1e-1);
+nothing
 ```
 
 Let's see what that looks like:
diff --git a/docs/src/index.md b/docs/src/index.md
index dcb787273..cd9086074 100644
--- a/docs/src/index.md
+++ b/docs/src/index.md
@@ -50,7 +50,7 @@ using Flux, Tracker
 x = [0.8; 0.8]
 ann = Chain(Dense(2, 10, tanh), Dense(10, 1))
 p, re = Flux.destructure(ann)
-z = re(Float64(p))
+z = re(Float64.(p))
 ```
 
 While one may think this recreates the neural network to act in `Float64` precision, [it does not](https://github.com/FluxML/Flux.jl/pull/2156)