Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2301. Min Range: -6.2301
Max Act: 6.2301. Min Act: -0.1700
Data Index: 8729717 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.8864. Min Act: -0.1700
Data Index: 6701457 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.8551. Min Act: -0.1700
Data Index: 6205683 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.6676. Min Act: -0.1700
Data Index: 6592213 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.6364. Min Act: -0.1700
Data Index: 8223862 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.6676. Min Act: -0.1700
Data Index: 1593884 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.6676. Min Act: -0.1700
Data Index: 4972309 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.6364. Min Act: -0.1700
Data Index: 6537276 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.6051. Min Act: -0.1700
Data Index: 6923405 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 762739 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 5795467 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 845268 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 5785455 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 5848460 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5426. Min Act: -0.1700
Data Index: 4877074 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5114. Min Act: -0.1700
Data Index: 112839 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5114. Min Act: -0.1700
Data Index: 2151168 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5114. Min Act: -0.1700
Data Index: 8663185 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.5114. Min Act: -0.1700
Data Index: 6327230 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2301. Min Range: -6.2301
Max Act: 5.4801. Min Act: -0.1700
Data Index: 3427292 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19