Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.6174. Min Act: -0.1700
Data Index: 2032627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5861. Min Act: -0.1700
Data Index: 6397041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.6174. Min Act: -0.1700
Data Index: 6058813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5861. Min Act: -0.1700
Data Index: 3731622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5861. Min Act: -0.1700
Data Index: 8682253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5861. Min Act: -0.1700
Data Index: 3389318 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5548. Min Act: -0.1700
Data Index: 4029796 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5235. Min Act: -0.1700
Data Index: 6663658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5235. Min Act: -0.1700
Data Index: 7138252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5235. Min Act: -0.1700
Data Index: 7675711 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5235. Min Act: -0.1700
Data Index: 7985195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.5235. Min Act: -0.1700
Data Index: 8674901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3168185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 6738309 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 977528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 4985501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 5750925 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 4271922 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 2237635 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6174. Min Range: -3.6174
Max Act: 3.4922. Min Act: -0.1700
Data Index: 5669937 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19