Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4359 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0223. Min Range: -4.0223
Max Act: 4.0223. Min Act: -0.1700
Data Index: 6811814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9911. Min Act: -0.1700
Data Index: 1599594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 6071285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8660. Min Act: -0.1700
Data Index: 3099139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8973. Min Act: -0.1700
Data Index: 4298142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8660. Min Act: -0.1700
Data Index: 6628001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8660. Min Act: -0.1700
Data Index: 1712048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8660. Min Act: -0.1700
Data Index: 1666326 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8660. Min Act: -0.1700
Data Index: 2533071 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 7865799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 5565508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8035. Min Act: -0.1700
Data Index: 5561089 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 6138968 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 6371045 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 4882328 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 2009663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 730007 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 1996176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8347. Min Act: -0.1700
Data Index: 4612760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8035. Min Act: -0.1700
Data Index: 2542706 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19