Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3900 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.9875. Min Act: -0.1700
Data Index: 6138265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.9562. Min Act: -0.1700
Data Index: 7045220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.9562. Min Act: -0.1700
Data Index: 1421957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.9562. Min Act: -0.1700
Data Index: 608577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.9562. Min Act: -0.1700
Data Index: 1151596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 896677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 2972269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 6966182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 1163947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 4115879 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 6293883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 2770886 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8937. Min Act: -0.1700
Data Index: 5048802 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 1278397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 1366264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 6229071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 2168160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 2394628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 6126971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9875. Min Range: -3.9875
Max Act: 3.8624. Min Act: -0.1700
Data Index: 5126412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19