Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4732 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.2971. Min Range: -10.2971
Max Act: 10.2971. Min Act: -0.1700
Data Index: 5131023 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2971. Min Range: -10.2971
Max Act: 10.2971. Min Act: -0.1700
Data Index: 4754285 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2971. Min Range: -10.2971
Max Act: 10.1721. Min Act: -0.1700
Data Index: 6370000 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2971. Min Range: -10.2971
Max Act: 10.1096. Min Act: -0.1700
Data Index: 2488441 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.7971. Min Act: -0.1700
Data Index: 1435983 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.7346. Min Act: -0.1700
Data Index: 5937379 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.7346. Min Act: -0.1700
Data Index: 3490671 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.6721. Min Act: -0.1700
Data Index: 1023710 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.6096. Min Act: -0.1700
Data Index: 7387241 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.6096. Min Act: -0.1700
Data Index: 723188 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.5471. Min Act: -0.1700
Data Index: 2655364 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.5471. Min Act: -0.1700
Data Index: 3105249 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.4846. Min Act: -0.1700
Data Index: 2913882 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.4221. Min Act: -0.1700
Data Index: 3490667 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.4221. Min Act: -0.1700
Data Index: 3490674 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.4221. Min Act: -0.1700
Data Index: 3671986 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.3596. Min Act: -0.1700
Data Index: 4754299 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.2346. Min Act: -0.1700
Data Index: 1726435 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.2346. Min Act: -0.1700
Data Index: 2157092 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2971. Min Range: -10.2971
Max Act: 9.2346. Min Act: -0.1700
Data Index: 2041687 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19