Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0298. Min Range: -3.0298
Max Act: 3.0298. Min Act: -0.1700
Data Index: 2008657 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0298. Min Range: -3.0298
Max Act: 3.0140. Min Act: -0.1700
Data Index: 6705589 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9982. Min Act: -0.1700
Data Index: 6840949 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9982. Min Act: -0.1700
Data Index: 8005588 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9666. Min Act: -0.1700
Data Index: 6843780 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9824. Min Act: -0.1700
Data Index: 5469829 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9349. Min Act: -0.1700
Data Index: 985728 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9349. Min Act: -0.1700
Data Index: 3887058 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9191. Min Act: -0.1700
Data Index: 4325207 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9191. Min Act: -0.1700
Data Index: 8704539 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.8873. Min Act: -0.1700
Data Index: 8051252 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9349. Min Act: -0.1700
Data Index: 4966523 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9191. Min Act: -0.1700
Data Index: 662137 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9032. Min Act: -0.1700
Data Index: 1857864 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9666. Min Act: -0.1700
Data Index: 7203134 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9032. Min Act: -0.1700
Data Index: 897136 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9191. Min Act: -0.1700
Data Index: 6174550 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9032. Min Act: -0.1700
Data Index: 4823177 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9191. Min Act: -0.1700
Data Index: 442612 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0298. Min Range: -3.0298
Max Act: 2.9191. Min Act: -0.1700
Data Index: 6988661 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19