Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4645 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.3534. Min Act: -0.1700
Data Index: 4251661 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.2597. Min Act: -0.1700
Data Index: 5338812 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.1972. Min Act: -0.1700
Data Index: 7396881 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.1659. Min Act: -0.1700
Data Index: 8474539 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.1347. Min Act: -0.1700
Data Index: 3662464 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0722. Min Act: -0.1700
Data Index: 5651656 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3534. Min Range: -6.3534
Max Act: 6.0409. Min Act: -0.1700
Data Index: 8442737 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9784. Min Act: -0.1700
Data Index: 532655 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9472. Min Act: -0.1700
Data Index: 5695413 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9472. Min Act: -0.1700
Data Index: 6802873 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9784. Min Act: -0.1700
Data Index: 2895353 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9159. Min Act: -0.1700
Data Index: 3733812 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9159. Min Act: -0.1700
Data Index: 444966 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.9159. Min Act: -0.1700
Data Index: 8416801 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.8847. Min Act: -0.1700
Data Index: 573560 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.8847. Min Act: -0.1700
Data Index: 261949 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.8222. Min Act: -0.1700
Data Index: 2655636 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.8534. Min Act: -0.1700
Data Index: 5345306 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1488640 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3534. Min Range: -6.3534
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2080547 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19