Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.4301. Min Act: -0.1700
Data Index: 5901880 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.3676. Min Act: -0.1700
Data Index: 6372970 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.3676. Min Act: -0.1700
Data Index: 2558196 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.3676. Min Act: -0.1700
Data Index: 5589779 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.3051. Min Act: -0.1700
Data Index: 7908938 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.3051. Min Act: -0.1700
Data Index: 3610313 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2738. Min Act: -0.1700
Data Index: 391135 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2426. Min Act: -0.1700
Data Index: 5589780 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2426. Min Act: -0.1700
Data Index: 1092587 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2426. Min Act: -0.1700
Data Index: 2123160 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2113. Min Act: -0.1700
Data Index: 264484 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2113. Min Act: -0.1700
Data Index: 257684 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2113. Min Act: -0.1700
Data Index: 1165496 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2113. Min Act: -0.1700
Data Index: 2437484 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2113. Min Act: -0.1700
Data Index: 2715734 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2426. Min Act: -0.1700
Data Index: 6919263 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.2113. Min Act: -0.1700
Data Index: 6991361 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.1801. Min Act: -0.1700
Data Index: 488629 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.1801. Min Act: -0.1700
Data Index: 5413990 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4301. Min Range: -6.4301
Max Act: 6.1801. Min Act: -0.1700
Data Index: 2332725 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19