A Many$-$to$-$ One RNN

Consider a many$-$to$-$one recurrent neural network with $20$ timesteps and a batch size of $32($batch size refers to the number of sequences fed into the network in one iteration$).$ The network architecture is as follows: $\backslash$table$[[\backslash$table$[[$Layer$],[$number$]],$Layer type,Number of neurons$],[0,$Input layer,$12],[1,$Hidden recurrent layer,$5],[2,$Hidden recurrent layer,$8],[3,$Output layer,$1]]$ what is size of a$^1(8)$ which is the activations sitting at layer $1$ and timestep $8?$