docstring fix following code review

theano/gpuarray/dnn.py

@@ -2464,7 +2464,7 @@ class RNNBlock(object):
         linear: input will be multiplied by a biased matrix
         skip: No operation is performed on the input.  The size must match the hidden size.
     direction_mode : {'unidirectional', 'bidirectional'}
-        unidirectional: The network operates recurrently from thefirst input to the last.
+        unidirectional: The network operates recurrently from the first input to the last.
         bidirectional: The network operates from first to last then from last to first and concatenates the results at each layer.
 
     """