Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1701 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.8190. Min Act: -0.1700
Data Index: 473186 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.7565. Min Act: -0.1700
Data Index: 1398123 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6628. Min Act: -0.1700
Data Index: 6007609 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6628. Min Act: -0.1700
Data Index: 1564420 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6315. Min Act: -0.1700
Data Index: 4638379 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6628. Min Act: -0.1700
Data Index: 1383522 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6628. Min Act: -0.1700
Data Index: 4096178 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6940. Min Act: -0.1700
Data Index: 1089893 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6315. Min Act: -0.1700
Data Index: 825922 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.6003. Min Act: -0.1700
Data Index: 1278941 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5378. Min Act: -0.1700
Data Index: 8109235 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5378. Min Act: -0.1700
Data Index: 1157882 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5378. Min Act: -0.1700
Data Index: 7679483 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5065. Min Act: -0.1700
Data Index: 810439 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5065. Min Act: -0.1700
Data Index: 3001015 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5065. Min Act: -0.1700
Data Index: 845743 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.4753. Min Act: -0.1700
Data Index: 4007057 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.4753. Min Act: -0.1700
Data Index: 88377 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.5065. Min Act: -0.1700
Data Index: 6390686 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8190. Min Range: -7.8190
Max Act: 7.4753. Min Act: -0.1700
Data Index: 3682920 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19