Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1102 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.0725. Min Range: -9.0725
Max Act: 9.0725. Min Act: -0.1700
Data Index: 8245507 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.8225. Min Act: -0.1700
Data Index: 1105645 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.6350. Min Act: -0.1700
Data Index: 125047 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.6350. Min Act: -0.1700
Data Index: 7072701 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.5725. Min Act: -0.1700
Data Index: 1476491 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.6350. Min Act: -0.1700
Data Index: 2832312 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.5725. Min Act: -0.1700
Data Index: 4033321 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.5100. Min Act: -0.1700
Data Index: 5747430 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.4475. Min Act: -0.1700
Data Index: 4440263 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.3225. Min Act: -0.1700
Data Index: 7681164 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.3850. Min Act: -0.1700
Data Index: 29016 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.3225. Min Act: -0.1700
Data Index: 2040599 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.3225. Min Act: -0.1700
Data Index: 2267848 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.2600. Min Act: -0.1700
Data Index: 3695115 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.2600. Min Act: -0.1700
Data Index: 6007998 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.3225. Min Act: -0.1700
Data Index: 5620503 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.1975. Min Act: -0.1700
Data Index: 2164889 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.2600. Min Act: -0.1700
Data Index: 4549303 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.2600. Min Act: -0.1700
Data Index: 3275905 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0725. Min Range: -9.0725
Max Act: 8.1350. Min Act: -0.1700
Data Index: 2762002 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19