Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0602. Min Range: -5.0602
Max Act: 5.0602. Min Act: -0.1700
Data Index: 4012370 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.8727. Min Act: -0.1700
Data Index: 4012365 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.7477. Min Act: -0.1700
Data Index: 2859446 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.7164. Min Act: -0.1700
Data Index: 4012366 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.6539. Min Act: -0.1700
Data Index: 4923969 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.6227. Min Act: -0.1700
Data Index: 693117 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.6539. Min Act: -0.1700
Data Index: 477273 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.6227. Min Act: -0.1700
Data Index: 1449964 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.5914. Min Act: -0.1700
Data Index: 1079698 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.5602. Min Act: -0.1700
Data Index: 5935866 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4977. Min Act: -0.1700
Data Index: 2184473 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4977. Min Act: -0.1700
Data Index: 4069493 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4977. Min Act: -0.1700
Data Index: 2697645 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.5289. Min Act: -0.1700
Data Index: 6225867 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4664. Min Act: -0.1700
Data Index: 577449 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 4084332 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 615980 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4352. Min Act: -0.1700
Data Index: 488903 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4664. Min Act: -0.1700
Data Index: 8467840 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0602. Min Range: -5.0602
Max Act: 4.4039. Min Act: -0.1700
Data Index: 5175298 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19