Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1503 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.6344. Min Act: -0.1700
Data Index: 1096497 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.5094. Min Act: -0.1700
Data Index: 6248023 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4156. Min Act: -0.1700
Data Index: 7540229 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3844. Min Act: -0.1700
Data Index: 6068479 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4156. Min Act: -0.1700
Data Index: 628343 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3531. Min Act: -0.1700
Data Index: 7010162 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.2906. Min Act: -0.1700
Data Index: 1014792 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.1969. Min Act: -0.1700
Data Index: 6526649 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.0719. Min Act: -0.1700
Data Index: 3773514 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.0406. Min Act: -0.1700
Data Index: 6381420 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.9781. Min Act: -0.1700
Data Index: 8568234 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.0094. Min Act: -0.1700
Data Index: 7122221 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.9781. Min Act: -0.1700
Data Index: 6470277 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.9781. Min Act: -0.1700
Data Index: 5858233 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.9156. Min Act: -0.1700
Data Index: 3487102 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.9156. Min Act: -0.1700
Data Index: 5586236 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.8844. Min Act: -0.1700
Data Index: 3921465 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.8531. Min Act: -0.1700
Data Index: 4696069 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.8531. Min Act: -0.1700
Data Index: 6079668 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6344. Min Range: -6.6344
Max Act: 5.8219. Min Act: -0.1700
Data Index: 5614661 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19