Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3273. Min Range: -6.3273
Max Act: 6.3273. Min Act: -0.1700
Data Index: 1775922 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.7648. Min Act: -0.1700
Data Index: 8081181 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.6710. Min Act: -0.1700
Data Index: 2468019 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.6710. Min Act: -0.1700
Data Index: 431326 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.6085. Min Act: -0.1700
Data Index: 7602817 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.5460. Min Act: -0.1700
Data Index: 266515 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.5773. Min Act: -0.1700
Data Index: 2538058 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.4523. Min Act: -0.1700
Data Index: 4670885 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.4210. Min Act: -0.1700
Data Index: 7928749 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.4210. Min Act: -0.1700
Data Index: 962455 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 6606940 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 7127289 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3898. Min Act: -0.1700
Data Index: 8504158 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3273. Min Act: -0.1700
Data Index: 6127653 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3585. Min Act: -0.1700
Data Index: 7046849 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3585. Min Act: -0.1700
Data Index: 3622975 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3273. Min Act: -0.1700
Data Index: 861889 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.3273. Min Act: -0.1700
Data Index: 6877369 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.2960. Min Act: -0.1700
Data Index: 8129917 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3273. Min Range: -6.3273
Max Act: 5.2648. Min Act: -0.1700
Data Index: 6173036 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19