Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4161 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0878. Min Range: -7.0878
Max Act: 7.0878. Min Act: -0.1700
Data Index: 7141470 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6816. Min Act: -0.1700
Data Index: 3498534 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6191. Min Act: -0.1700
Data Index: 1842779 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5878. Min Act: -0.1700
Data Index: 4483417 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4941. Min Act: -0.1700
Data Index: 6699300 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4941. Min Act: -0.1700
Data Index: 8436496 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4628. Min Act: -0.1700
Data Index: 5378932 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4316. Min Act: -0.1700
Data Index: 1365080 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4628. Min Act: -0.1700
Data Index: 540512 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4316. Min Act: -0.1700
Data Index: 5781070 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3691. Min Act: -0.1700
Data Index: 410525 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3691. Min Act: -0.1700
Data Index: 3476871 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3691. Min Act: -0.1700
Data Index: 7894334 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3691. Min Act: -0.1700
Data Index: 5752480 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3378. Min Act: -0.1700
Data Index: 1797097 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3378. Min Act: -0.1700
Data Index: 6093976 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3378. Min Act: -0.1700
Data Index: 3007163 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3378. Min Act: -0.1700
Data Index: 4998003 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.2753. Min Act: -0.1700
Data Index: 692755 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.2753. Min Act: -0.1700
Data Index: 2286161 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19