Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2871. Min Range: -6.2871
Max Act: 6.2871. Min Act: -0.1700
Data Index: 6250472 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2871. Min Range: -6.2871
Max Act: 6.2246. Min Act: -0.1700
Data Index: 5403166 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2871. Min Range: -6.2871
Max Act: 6.0996. Min Act: -0.1700
Data Index: 2685501 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2871. Min Range: -6.2871
Max Act: 6.0683. Min Act: -0.1700
Data Index: 7710879 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.8808. Min Act: -0.1700
Data Index: 6350405 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.7558. Min Act: -0.1700
Data Index: 1645586 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.7246. Min Act: -0.1700
Data Index: 7483046 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.7246. Min Act: -0.1700
Data Index: 2359223 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.6621. Min Act: -0.1700
Data Index: 1711717 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5996. Min Act: -0.1700
Data Index: 2871743 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 6345482 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 1382593 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 6640423 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5683. Min Act: -0.1700
Data Index: 4298852 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5996. Min Act: -0.1700
Data Index: 1991253 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5371. Min Act: -0.1700
Data Index: 3363168 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5058. Min Act: -0.1700
Data Index: 6358068 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5058. Min Act: -0.1700
Data Index: 7663911 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5371. Min Act: -0.1700
Data Index: 2950454 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2871. Min Range: -6.2871
Max Act: 5.5058. Min Act: -0.1700
Data Index: 5310796 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19