Back Propagation

[CodingIsFun]

Hi, I'd like to know why exactly my back propagation function keeps giving the same pattern of weights for every neuron of the same layer (except the first layer, it's different because it has non-linear activation functions).
This is the sheet with the weights:

1.xlsx

Hoja1 X,Time,Kappa,Epsilon.0-0,Epsilon.0-1,Epsilon.0-2,Epsilon.0-3,Epsilon.0-4,Epsilon.0-5,Epsilon.1-0,Epsilon.1-1,Epsilon.1-2,Epsilon.1-3,Epsilon.1-4,Epsilon.2-0,Epsilon.2-1,Epsilon.2-2,Epsilon.3-0,Epsilon.3-1,Weight.0-0-0 0,2,33E-04,1,-862,44446,-862,44446,-862,44446,-862,44446,-862,44446,-862...

docs.google.com

If I knew how to, I would post the code. If it's needed I'll try to figure out how to post it.