Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5537 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1245. Min Range: -7.1245
Max Act: 7.1245. Min Act: -0.1700
Data Index: 5499492 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1245. Min Range: -7.1245
Max Act: 7.1245. Min Act: -0.1700
Data Index: 3612898 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.9995. Min Act: -0.1700
Data Index: 2443722 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.6557. Min Act: -0.1700
Data Index: 6698980 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.5620. Min Act: -0.1700
Data Index: 6142441 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.5620. Min Act: -0.1700
Data Index: 4539197 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.5620. Min Act: -0.1700
Data Index: 7988717 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.5620. Min Act: -0.1700
Data Index: 258593 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4995. Min Act: -0.1700
Data Index: 1283088 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4682. Min Act: -0.1700
Data Index: 403369 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4995. Min Act: -0.1700
Data Index: 854575 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4682. Min Act: -0.1700
Data Index: 4262431 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4682. Min Act: -0.1700
Data Index: 2634081 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4370. Min Act: -0.1700
Data Index: 8541836 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4370. Min Act: -0.1700
Data Index: 4007603 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4057. Min Act: -0.1700
Data Index: 1604104 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.4057. Min Act: -0.1700
Data Index: 295900 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.3432. Min Act: -0.1700
Data Index: 1954353 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.2807. Min Act: -0.1700
Data Index: 7207761 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1245. Min Range: -7.1245
Max Act: 6.2807. Min Act: -0.1700
Data Index: 6659607 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19