Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3188. Min Range: -7.3188
Max Act: 7.3188. Min Act: -0.1700
Data Index: 2325989 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3188. Min Range: -7.3188
Max Act: 7.0688. Min Act: -0.1700
Data Index: 7185246 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3188. Min Range: -7.3188
Max Act: 7.0376. Min Act: -0.1700
Data Index: 6375303 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3188. Min Range: -7.3188
Max Act: 7.0063. Min Act: -0.1700
Data Index: 1769082 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3188. Min Range: -7.3188
Max Act: 7.0063. Min Act: -0.1700
Data Index: 809181 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.9751. Min Act: -0.1700
Data Index: 839048 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.9438. Min Act: -0.1700
Data Index: 6504164 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.9126. Min Act: -0.1700
Data Index: 5129326 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.9126. Min Act: -0.1700
Data Index: 3013990 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.8813. Min Act: -0.1700
Data Index: 1065671 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.8501. Min Act: -0.1700
Data Index: 7488662 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.8501. Min Act: -0.1700
Data Index: 4960409 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.8188. Min Act: -0.1700
Data Index: 305447 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.8188. Min Act: -0.1700
Data Index: 6247479 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.7876. Min Act: -0.1700
Data Index: 4117861 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.7876. Min Act: -0.1700
Data Index: 1571846 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.7251. Min Act: -0.1700
Data Index: 5883885 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.7563. Min Act: -0.1700
Data Index: 1689287 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.7251. Min Act: -0.1700
Data Index: 5750419 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3188. Min Range: -7.3188
Max Act: 6.6626. Min Act: -0.1700
Data Index: 2332514 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19