diff --git a/python/paddle/nn/layer/rnn.py b/python/paddle/nn/layer/rnn.py
index ee989f27ebf72a20a16b575ee9be30b694f0d483..75817aa2dc227877fd97fb24ecd4cfa431659be6 100644
--- a/python/paddle/nn/layer/rnn.py
+++ b/python/paddle/nn/layer/rnn.py
@@ -582,11 +582,11 @@ class GRUCell(RNNCellBase):
 
     ..  math::
 
-        r_{t} & = \sigma(W_{ir}x_{t} + b_{ir} + W_{hr}x_{t} + b_{hr})
+        r_{t} & = \sigma(W_{ir}x_{t} + b_{ir} + W_{hr}x_{t-1} + b_{hr})
 
-        z_{t} & = \sigma(W_{iz}x_{t} + b_{iz} + W_{hz}x_{t} + b_{hz})
+        z_{t} & = \sigma(W_{iz}x_{t} + b_{iz} + W_{hz}x_{t-1} + b_{hz})
 
-        \widetilde{h}_{t} & = \tanh(W_{ic}x_{t} + b_{ic} + r_{t} * (W_{hc}x_{t} + b_{hc}))
+        \widetilde{h}_{t} & = \tanh(W_{ic}x_{t} + b_{ic} + r_{t} * (W_{hc}x_{t-1} + b_{hc}))
 
         h_{t} & = z_{t} * h_{t-1} + (1 - z_{t}) * \widetilde{h}_{t}
 
@@ -1413,11 +1413,11 @@ class GRU(RNNBase):
 
     .. math::
 
-        r_{t} & = \sigma(W_{ir}x_{t} + b_{ir} + W_{hr}x_{t} + b_{hr})
+        r_{t} & = \sigma(W_{ir}x_{t} + b_{ir} + W_{hr}x_{t-1} + b_{hr})
 
-        z_{t} & = \sigma(W_{iz}x_{t} + b_{iz} + W_{hz}x_{t} + b_{hz})
+        z_{t} & = \sigma(W_{iz}x_{t} + b_{iz} + W_{hz}x_{t-1} + b_{hz})
 
-        \widetilde{h}_{t} & = \tanh(W_{ic}x_{t} + b_{ic} + r_{t} * (W_{hc}x_{t} + b_{hc}))
+        \widetilde{h}_{t} & = \tanh(W_{ic}x_{t} + b_{ic} + r_{t} * (W_{hc}x_{t-1} + b_{hc}))
 
         h_{t} & = z_{t} * h_{t-1} + (1 - z_{t}) * \widetilde{h}_{t}