Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.5938. Min Act: -0.1700
Data Index: 5093748 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.0626. Min Act: -0.1700
Data Index: 6191186 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.6251. Min Act: -0.1700
Data Index: 2924306 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.2813. Min Act: -0.1700
Data Index: 7392000 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.1876. Min Act: -0.1700
Data Index: 131083 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.0626. Min Act: -0.1700
Data Index: 2827342 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6251. Min Range: -6.6251
Max Act: 6.0001. Min Act: -0.1700
Data Index: 23163 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.9688. Min Act: -0.1700
Data Index: 1890165 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.8751. Min Act: -0.1700
Data Index: 8274606 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.8751. Min Act: -0.1700
Data Index: 6406481 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.7813. Min Act: -0.1700
Data Index: 776922 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.7501. Min Act: -0.1700
Data Index: 6469907 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.7813. Min Act: -0.1700
Data Index: 1678575 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.7813. Min Act: -0.1700
Data Index: 4250183 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.0001. Min Act: -0.1700
Data Index: 3866772 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.3438. Min Act: -0.1700
Data Index: 867407 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.6563. Min Act: -0.1700
Data Index: 179117 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.5626. Min Act: -0.1700
Data Index: 414073 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.4688. Min Act: -0.1700
Data Index: 3894148 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6251. Min Range: -6.6251
Max Act: 5.6563. Min Act: -0.1700
Data Index: 7818748 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19