What receives a LSTM neuron?

Question

I'm confused about input data on LSTM neurons. I know that exist almost two form to give data to a recurrent neural network.

I want to understand with a example

Data
[1,2,3,4,5,6]

For feeda RNN, data must be formatted with this schema:

(x,y,z)
    x = samples
    y = timestep
    z = features

But, I know three ways to input data:

Way 1
Shape = (x,1,3)

data = [
        [[1,2,3]],
        [[2,3,4]],
        [[3,4,5]],
        [[4,5,6]],      
        ]

Way 2
Shape = (x,3,1)

data = [
        [[1],[2],[3]],
        [[2],[3],[4]],
        [[3],[4],[5]],
        [[4],[5],[6]],      
        ]

Way 3
Shape = (x,2,2)

data = [
        [[1,2],[3,4]],
        [[2,3],[4,5]],
        [[3,4],[5,6]],      
        ]

If input is way 1, I supose LSTM neurons = z.

But I don't know what receive the neurons in way 2 and 3.