Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 449 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.2501. Min Act: -0.1700
Data Index: 2254503 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.1876. Min Act: -0.1700
Data Index: 1246181 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.1876. Min Act: -0.1700
Data Index: 277365 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.1251. Min Act: -0.1700
Data Index: 8504802 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.1251. Min Act: -0.1700
Data Index: 4650427 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.0001. Min Act: -0.1700
Data Index: 7832041 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2501. Min Range: -9.2501
Max Act: 9.0001. Min Act: -0.1700
Data Index: 3997223 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.9376. Min Act: -0.1700
Data Index: 2044312 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.9376. Min Act: -0.1700
Data Index: 2372044 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.9376. Min Act: -0.1700
Data Index: 4659205 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.8751. Min Act: -0.1700
Data Index: 1726734 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.8126. Min Act: -0.1700
Data Index: 263880 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.7501. Min Act: -0.1700
Data Index: 4160974 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.7501. Min Act: -0.1700
Data Index: 891979 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.8126. Min Act: -0.1700
Data Index: 37036 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.7501. Min Act: -0.1700
Data Index: 3144558 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.7501. Min Act: -0.1700
Data Index: 8707349 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.6876. Min Act: -0.1700
Data Index: 7440689 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.6876. Min Act: -0.1700
Data Index: 3457351 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2501. Min Range: -9.2501
Max Act: 8.5626. Min Act: -0.1700
Data Index: 2883045 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19