Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0252. Min Range: -6.0252
Max Act: 6.0252. Min Act: -0.1700
Data Index: 2829772 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.8689. Min Act: -0.1700
Data Index: 1931864 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.8064. Min Act: -0.1700
Data Index: 394814 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.8064. Min Act: -0.1700
Data Index: 79959 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.7439. Min Act: -0.1700
Data Index: 2165379 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6814. Min Act: -0.1700
Data Index: 2622067 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.7127. Min Act: -0.1700
Data Index: 3813035 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6814. Min Act: -0.1700
Data Index: 4328424 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6814. Min Act: -0.1700
Data Index: 8799352 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6814. Min Act: -0.1700
Data Index: 2102514 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6502. Min Act: -0.1700
Data Index: 8360225 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6502. Min Act: -0.1700
Data Index: 8167554 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6502. Min Act: -0.1700
Data Index: 6112875 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6502. Min Act: -0.1700
Data Index: 8025401 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6189. Min Act: -0.1700
Data Index: 1801074 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6189. Min Act: -0.1700
Data Index: 4746144 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6189. Min Act: -0.1700
Data Index: 1270279 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.6189. Min Act: -0.1700
Data Index: 3711515 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.5564. Min Act: -0.1700
Data Index: 200453 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0252. Min Range: -6.0252
Max Act: 5.5877. Min Act: -0.1700
Data Index: 1380139 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19