Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2790. Min Range: -5.2790
Max Act: 5.2790. Min Act: -0.1700
Data Index: 2229364 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.9353. Min Act: -0.1700
Data Index: 583607 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.9040. Min Act: -0.1700
Data Index: 5931196 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.9040. Min Act: -0.1700
Data Index: 7485139 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.7478. Min Act: -0.1700
Data Index: 7963000 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.7165. Min Act: -0.1700
Data Index: 3367657 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.7478. Min Act: -0.1700
Data Index: 5925031 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.7165. Min Act: -0.1700
Data Index: 6639071 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6853. Min Act: -0.1700
Data Index: 664440 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6540. Min Act: -0.1700
Data Index: 5443687 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6540. Min Act: -0.1700
Data Index: 3664733 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6540. Min Act: -0.1700
Data Index: 2462912 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6540. Min Act: -0.1700
Data Index: 8296354 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6228. Min Act: -0.1700
Data Index: 1680700 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6228. Min Act: -0.1700
Data Index: 885079 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.6228. Min Act: -0.1700
Data Index: 6155645 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.5915. Min Act: -0.1700
Data Index: 7280177 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.5603. Min Act: -0.1700
Data Index: 2068653 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.5915. Min Act: -0.1700
Data Index: 2404551 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2790. Min Range: -5.2790
Max Act: 4.5915. Min Act: -0.1700
Data Index: 4790781 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19