Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6030 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1426. Min Range: -6.1426
Max Act: 6.1426. Min Act: -0.1700
Data Index: 4417633 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1426. Min Range: -6.1426
Max Act: 6.1426. Min Act: -0.1700
Data Index: 2847212 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1426. Min Range: -6.1426
Max Act: 6.0801. Min Act: -0.1700
Data Index: 1630501 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1426. Min Range: -6.1426
Max Act: 6.0489. Min Act: -0.1700
Data Index: 5270208 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9864. Min Act: -0.1700
Data Index: 2534111 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1426. Min Range: -6.1426
Max Act: 6.0176. Min Act: -0.1700
Data Index: 1296975 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9864. Min Act: -0.1700
Data Index: 280999 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9864. Min Act: -0.1700
Data Index: 4204426 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9551. Min Act: -0.1700
Data Index: 2614669 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9551. Min Act: -0.1700
Data Index: 4718839 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9551. Min Act: -0.1700
Data Index: 923531 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9551. Min Act: -0.1700
Data Index: 8103890 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9551. Min Act: -0.1700
Data Index: 663964 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9239. Min Act: -0.1700
Data Index: 8103891 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9551. Min Act: -0.1700
Data Index: 4773924 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.9239. Min Act: -0.1700
Data Index: 1877269 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.8926. Min Act: -0.1700
Data Index: 4718838 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.8926. Min Act: -0.1700
Data Index: 2621349 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.8926. Min Act: -0.1700
Data Index: 6010144 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1426. Min Range: -6.1426
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1725820 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19