Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 635 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.9996. Min Act: -0.1700
Data Index: 3129392 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.9059. Min Act: -0.1700
Data Index: 25462 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.9059. Min Act: -0.1700
Data Index: 422766 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.7496. Min Act: -0.1700
Data Index: 508899 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6871. Min Act: -0.1700
Data Index: 1229730 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6871. Min Act: -0.1700
Data Index: 1536672 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6559. Min Act: -0.1700
Data Index: 8299356 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6559. Min Act: -0.1700
Data Index: 910016 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6559. Min Act: -0.1700
Data Index: 5398411 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6246. Min Act: -0.1700
Data Index: 3236262 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6246. Min Act: -0.1700
Data Index: 8312070 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.6246. Min Act: -0.1700
Data Index: 3279952 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5934. Min Act: -0.1700
Data Index: 7438460 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5934. Min Act: -0.1700
Data Index: 4421758 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5621. Min Act: -0.1700
Data Index: 1226350 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5934. Min Act: -0.1700
Data Index: 7347215 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5309. Min Act: -0.1700
Data Index: 4265023 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5621. Min Act: -0.1700
Data Index: 419709 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5309. Min Act: -0.1700
Data Index: 4141025 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9996. Min Range: -5.9996
Max Act: 5.5309. Min Act: -0.1700
Data Index: 6244568 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19