Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.7368. Min Act: -0.1700
Data Index: 1079791 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.5805. Min Act: -0.1700
Data Index: 1328281 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.5180. Min Act: -0.1700
Data Index: 8800252 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.4555. Min Act: -0.1700
Data Index: 6763241 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.3618. Min Act: -0.1700
Data Index: 5381212 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.3618. Min Act: -0.1700
Data Index: 6136225 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.3618. Min Act: -0.1700
Data Index: 5734816 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.2680. Min Act: -0.1700
Data Index: 2179032 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.3305. Min Act: -0.1700
Data Index: 547803 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.2680. Min Act: -0.1700
Data Index: 5322817 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.2368. Min Act: -0.1700
Data Index: 6195217 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.2055. Min Act: -0.1700
Data Index: 6017403 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1743. Min Act: -0.1700
Data Index: 8747119 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1743. Min Act: -0.1700
Data Index: 2876461 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1743. Min Act: -0.1700
Data Index: 36608 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1118. Min Act: -0.1700
Data Index: 146401 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1430. Min Act: -0.1700
Data Index: 6929517 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1430. Min Act: -0.1700
Data Index: 5993755 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1118. Min Act: -0.1700
Data Index: 4425165 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7368. Min Range: -6.7368
Max Act: 6.1118. Min Act: -0.1700
Data Index: 999127 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19