Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.8102. Min Act: -0.1700
Data Index: 4507700 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.6227. Min Act: -0.1700
Data Index: 6185054 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.5289. Min Act: -0.1700
Data Index: 301747 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.4977. Min Act: -0.1700
Data Index: 1109195 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.4352. Min Act: -0.1700
Data Index: 6465396 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.3727. Min Act: -0.1700
Data Index: 8421651 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.3414. Min Act: -0.1700
Data Index: 4361981 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.3102. Min Act: -0.1700
Data Index: 8316767 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.3102. Min Act: -0.1700
Data Index: 4361974 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1852. Min Act: -0.1700
Data Index: 4654802 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1852. Min Act: -0.1700
Data Index: 5359324 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1852. Min Act: -0.1700
Data Index: 1150596 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1539. Min Act: -0.1700
Data Index: 4566748 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1539. Min Act: -0.1700
Data Index: 472398 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1539. Min Act: -0.1700
Data Index: 1842490 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.1227. Min Act: -0.1700
Data Index: 2154832 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.0914. Min Act: -0.1700
Data Index: 808027 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.0914. Min Act: -0.1700
Data Index: 1260455 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.0914. Min Act: -0.1700
Data Index: 930886 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8102. Min Range: -7.8102
Max Act: 7.0914. Min Act: -0.1700
Data Index: 1099281 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19