Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0914. Min Range: -5.0914
Max Act: 5.0914. Min Act: -0.1700
Data Index: 7508783 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0914. Min Range: -5.0914
Max Act: 5.0602. Min Act: -0.1700
Data Index: 3910855 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.9977. Min Act: -0.1700
Data Index: 6618338 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.9664. Min Act: -0.1700
Data Index: 8617801 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.9352. Min Act: -0.1700
Data Index: 7944289 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.9039. Min Act: -0.1700
Data Index: 930239 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.8414. Min Act: -0.1700
Data Index: 5999336 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.8727. Min Act: -0.1700
Data Index: 8341370 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.8414. Min Act: -0.1700
Data Index: 7669790 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.8414. Min Act: -0.1700
Data Index: 4607267 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.8102. Min Act: -0.1700
Data Index: 396187 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7789. Min Act: -0.1700
Data Index: 8497488 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.8102. Min Act: -0.1700
Data Index: 6923123 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7789. Min Act: -0.1700
Data Index: 258502 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7789. Min Act: -0.1700
Data Index: 2509607 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7789. Min Act: -0.1700
Data Index: 3731993 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7789. Min Act: -0.1700
Data Index: 3360974 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7477. Min Act: -0.1700
Data Index: 1839924 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7789. Min Act: -0.1700
Data Index: 4588083 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0914. Min Range: -5.0914
Max Act: 4.7477. Min Act: -0.1700
Data Index: 8068389 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19