Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6564. Min Range: -8.6564
Max Act: 8.6564. Min Act: -0.1700
Data Index: 6277200 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6564. Min Range: -8.6564
Max Act: 8.3439. Min Act: -0.1700
Data Index: 2324105 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6564. Min Range: -8.6564
Max Act: 8.0626. Min Act: -0.1700
Data Index: 3816551 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9689. Min Act: -0.1700
Data Index: 6551739 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9064. Min Act: -0.1700
Data Index: 7050842 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9376. Min Act: -0.1700
Data Index: 681566 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9064. Min Act: -0.1700
Data Index: 2470883 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9064. Min Act: -0.1700
Data Index: 751106 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9376. Min Act: -0.1700
Data Index: 8739487 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.8751. Min Act: -0.1700
Data Index: 6098360 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.8751. Min Act: -0.1700
Data Index: 6055617 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.9064. Min Act: -0.1700
Data Index: 1201535 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.8439. Min Act: -0.1700
Data Index: 8477435 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.7814. Min Act: -0.1700
Data Index: 2567973 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.7501. Min Act: -0.1700
Data Index: 7223580 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.7501. Min Act: -0.1700
Data Index: 8348075 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.7189. Min Act: -0.1700
Data Index: 8739489 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.6876. Min Act: -0.1700
Data Index: 1003584 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.6564. Min Act: -0.1700
Data Index: 8136077 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6564. Min Range: -8.6564
Max Act: 7.6564. Min Act: -0.1700
Data Index: 7463729 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19