Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.3346. Min Act: -0.1700
Data Index: 971129 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.3034. Min Act: -0.1700
Data Index: 3437714 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.3346. Min Act: -0.1700
Data Index: 5460678 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2409. Min Act: -0.1700
Data Index: 4310645 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2721. Min Act: -0.1700
Data Index: 6856231 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2721. Min Act: -0.1700
Data Index: 7162649 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2409. Min Act: -0.1700
Data Index: 5286839 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2409. Min Act: -0.1700
Data Index: 3985043 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2096. Min Act: -0.1700
Data Index: 1656290 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2096. Min Act: -0.1700
Data Index: 3527084 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.1784. Min Act: -0.1700
Data Index: 7065994 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.2096. Min Act: -0.1700
Data Index: 4484779 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.1784. Min Act: -0.1700
Data Index: 7886279 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.1471. Min Act: -0.1700
Data Index: 3349357 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.1159. Min Act: -0.1700
Data Index: 3405592 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.1159. Min Act: -0.1700
Data Index: 2815723 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.0846. Min Act: -0.1700
Data Index: 7471327 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.0846. Min Act: -0.1700
Data Index: 2484264 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.0534. Min Act: -0.1700
Data Index: 3792587 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3346. Min Range: -6.3346
Max Act: 6.0846. Min Act: -0.1700
Data Index: 3792586 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19