Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5301. Min Range: -8.5301
Max Act: 8.5301. Min Act: -0.1700
Data Index: 3398374 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5301. Min Range: -8.5301
Max Act: 8.1239. Min Act: -0.1700
Data Index: 2020204 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5301. Min Range: -8.5301
Max Act: 8.0614. Min Act: -0.1700
Data Index: 3799626 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5301. Min Range: -8.5301
Max Act: 8.0614. Min Act: -0.1700
Data Index: 7300646 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.9676. Min Act: -0.1700
Data Index: 8365639 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.9364. Min Act: -0.1700
Data Index: 1975997 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.8739. Min Act: -0.1700
Data Index: 1731402 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.9051. Min Act: -0.1700
Data Index: 1396572 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.7176. Min Act: -0.1700
Data Index: 5396972 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6864. Min Act: -0.1700
Data Index: 760034 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.7176. Min Act: -0.1700
Data Index: 1222781 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6864. Min Act: -0.1700
Data Index: 3609589 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6551. Min Act: -0.1700
Data Index: 3990569 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6864. Min Act: -0.1700
Data Index: 4664076 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6239. Min Act: -0.1700
Data Index: 791440 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6239. Min Act: -0.1700
Data Index: 7145522 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.6551. Min Act: -0.1700
Data Index: 4756813 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.5926. Min Act: -0.1700
Data Index: 4730517 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.5301. Min Act: -0.1700
Data Index: 4420577 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5301. Min Range: -8.5301
Max Act: 7.5614. Min Act: -0.1700
Data Index: 3222883 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19