Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2508 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.3369. Min Act: -0.1700
Data Index: 4501737 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.3055. Min Act: -0.1700
Data Index: 2155049 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.3055. Min Act: -0.1700
Data Index: 3387788 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.2427. Min Act: -0.1700
Data Index: 6821542 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.2427. Min Act: -0.1700
Data Index: 4271324 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.2270. Min Act: -0.1700
Data Index: 3423750 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.2112. Min Act: -0.1700
Data Index: 1762095 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.2112. Min Act: -0.1700
Data Index: 4443703 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.2112. Min Act: -0.1700
Data Index: 579201 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1955. Min Act: -0.1700
Data Index: 5988072 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1955. Min Act: -0.1700
Data Index: 5691184 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1798. Min Act: -0.1700
Data Index: 500635 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1955. Min Act: -0.1700
Data Index: 7392550 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1640. Min Act: -0.1700
Data Index: 1980833 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1483. Min Act: -0.1700
Data Index: 1040309 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1483. Min Act: -0.1700
Data Index: 22637 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1483. Min Act: -0.1700
Data Index: 4065693 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1483. Min Act: -0.1700
Data Index: 1068754 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1483. Min Act: -0.1700
Data Index: 6693733 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3369. Min Range: -3.3369
Max Act: 3.1326. Min Act: -0.1700
Data Index: 6835498 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19