What weights do I use while backpropagating?

I’ve started to learn about neural networks recently and I can’t find the answer to this question.

Let’s assume there’s a neural network (fig. 1) Figure 1

So if the loss function is: Loss function

and the derivative deriv is: Derivative definition

if I want to use this to find dE/dw122 what k and l (well there’s only one neuron with index l here, but what if there would be more?) should i use in w^3_kl and w^2_jk?

Sorry if I failed to explain my problem. If something isn’t clear please ask in comments.