Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4856. Min Range: -10.4856
Max Act: 10.4856. Min Act: -0.1700
Data Index: 7589172 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.9856. Min Act: -0.1700
Data Index: 7112004 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.9231. Min Act: -0.1700
Data Index: 6644026 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.8606. Min Act: -0.1700
Data Index: 8745051 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.7981. Min Act: -0.1700
Data Index: 655940 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.7981. Min Act: -0.1700
Data Index: 8739379 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.7356. Min Act: -0.1700
Data Index: 5470657 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.5481. Min Act: -0.1700
Data Index: 4255826 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.5481. Min Act: -0.1700
Data Index: 3120469 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.5481. Min Act: -0.1700
Data Index: 7673232 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.4856. Min Act: -0.1700
Data Index: 6697307 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.4231. Min Act: -0.1700
Data Index: 6989643 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.3606. Min Act: -0.1700
Data Index: 6279240 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.3606. Min Act: -0.1700
Data Index: 7030071 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.3606. Min Act: -0.1700
Data Index: 7012535 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.3606. Min Act: -0.1700
Data Index: 1618291 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.2981. Min Act: -0.1700
Data Index: 280156 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.2981. Min Act: -0.1700
Data Index: 8255971 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.2981. Min Act: -0.1700
Data Index: 3908127 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4856. Min Range: -10.4856
Max Act: 9.2981. Min Act: -0.1700
Data Index: 7156969 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19