Neural Net Inputs.

My input is actually a series of 1's and 2's very long like 1600. I need to somehow reduce this to a manageable size, since if I use the entire array matlab is failing to train becuase it is too big. The input for e.g. is like [1 1 1 1 1 1 1 1 2 2 2 2 2 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 .......]... I also have half a dozen other inputs which of course I have no problem representing them adequately. I notice if I subtract 1 from each it becomes a binary number but still it would be humongous large number. Any helpful suggestion? Thanks in advance.