Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 919 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.9389. Min Act: -0.1700
Data Index: 7603314 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.5327. Min Act: -0.1700
Data Index: 4726489 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.5639. Min Act: -0.1700
Data Index: 8808315 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.5014. Min Act: -0.1700
Data Index: 7427089 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.3764. Min Act: -0.1700
Data Index: 2351579 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.2202. Min Act: -0.1700
Data Index: 7728742 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.2202. Min Act: -0.1700
Data Index: 4588940 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.1889. Min Act: -0.1700
Data Index: 5844041 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.1577. Min Act: -0.1700
Data Index: 3711388 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.1889. Min Act: -0.1700
Data Index: 4717227 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.1264. Min Act: -0.1700
Data Index: 2266926 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0639. Min Act: -0.1700
Data Index: 5920983 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0639. Min Act: -0.1700
Data Index: 376542 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0327. Min Act: -0.1700
Data Index: 5527979 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0639. Min Act: -0.1700
Data Index: 5475169 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0327. Min Act: -0.1700
Data Index: 8156178 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0014. Min Act: -0.1700
Data Index: 1963337 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0327. Min Act: -0.1700
Data Index: 2998135 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9389. Min Range: -6.9389
Max Act: 6.0014. Min Act: -0.1700
Data Index: 499690 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9389. Min Range: -6.9389
Max Act: 5.9702. Min Act: -0.1700
Data Index: 5459289 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19