Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.4234. Min Act: -0.1700
Data Index: 1985377 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.4234. Min Act: -0.1700
Data Index: 2983342 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.3609. Min Act: -0.1700
Data Index: 7109833 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.2359. Min Act: -0.1700
Data Index: 3892151 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.1421. Min Act: -0.1700
Data Index: 5247330 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.1109. Min Act: -0.1700
Data Index: 6991085 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.0171. Min Act: -0.1700
Data Index: 7775812 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4234. Min Range: -6.4234
Max Act: 6.0171. Min Act: -0.1700
Data Index: 1921314 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9859. Min Act: -0.1700
Data Index: 5273632 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9546. Min Act: -0.1700
Data Index: 1816163 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9546. Min Act: -0.1700
Data Index: 8173272 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9546. Min Act: -0.1700
Data Index: 282815 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9546. Min Act: -0.1700
Data Index: 8360410 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9234. Min Act: -0.1700
Data Index: 7318689 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9234. Min Act: -0.1700
Data Index: 8644021 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9234. Min Act: -0.1700
Data Index: 3396928 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.9234. Min Act: -0.1700
Data Index: 3706244 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.8921. Min Act: -0.1700
Data Index: 7548442 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.8921. Min Act: -0.1700
Data Index: 951459 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4234. Min Range: -6.4234
Max Act: 5.8609. Min Act: -0.1700
Data Index: 6995983 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19