Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0479. Min Range: -4.0479
Max Act: 4.0479. Min Act: -0.1700
Data Index: 6532746 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.9228. Min Act: -0.1700
Data Index: 4945400 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.8916. Min Act: -0.1700
Data Index: 7625909 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.8759. Min Act: -0.1700
Data Index: 8525301 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.8134. Min Act: -0.1700
Data Index: 1066490 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7977. Min Act: -0.1700
Data Index: 4246289 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7665. Min Act: -0.1700
Data Index: 196082 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7508. Min Act: -0.1700
Data Index: 5044204 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7352. Min Act: -0.1700
Data Index: 3463812 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7508. Min Act: -0.1700
Data Index: 1944256 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7352. Min Act: -0.1700
Data Index: 5086547 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7352. Min Act: -0.1700
Data Index: 227853 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7039. Min Act: -0.1700
Data Index: 2315162 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7195. Min Act: -0.1700
Data Index: 1440444 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.7195. Min Act: -0.1700
Data Index: 7747957 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.6883. Min Act: -0.1700
Data Index: 6994785 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.6726. Min Act: -0.1700
Data Index: 4040600 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.6726. Min Act: -0.1700
Data Index: 4056712 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.6726. Min Act: -0.1700
Data Index: 3732988 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0479. Min Range: -4.0479
Max Act: 3.6883. Min Act: -0.1700
Data Index: 5655821 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19