Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0679. Min Range: -8.0679
Max Act: 8.0679. Min Act: -0.1700
Data Index: 6865357 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.7241. Min Act: -0.1700
Data Index: 7453209 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.6304. Min Act: -0.1700
Data Index: 5931021 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.5679. Min Act: -0.1700
Data Index: 7672372 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.5991. Min Act: -0.1700
Data Index: 6245272 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.5366. Min Act: -0.1700
Data Index: 7531233 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.5679. Min Act: -0.1700
Data Index: 8029806 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.4429. Min Act: -0.1700
Data Index: 1658923 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.4429. Min Act: -0.1700
Data Index: 4308464 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.4116. Min Act: -0.1700
Data Index: 4952960 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.4116. Min Act: -0.1700
Data Index: 786479 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.4429. Min Act: -0.1700
Data Index: 3348701 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3804. Min Act: -0.1700
Data Index: 4923203 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3804. Min Act: -0.1700
Data Index: 8481679 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3804. Min Act: -0.1700
Data Index: 7488984 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3804. Min Act: -0.1700
Data Index: 281551 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3491. Min Act: -0.1700
Data Index: 1252360 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3491. Min Act: -0.1700
Data Index: 8216196 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3491. Min Act: -0.1700
Data Index: 7460303 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0679. Min Range: -8.0679
Max Act: 7.3179. Min Act: -0.1700
Data Index: 5128100 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19