Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0236. Min Range: -7.0236
Max Act: 7.0236. Min Act: -0.1700
Data Index: 4095628 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.8049. Min Act: -0.1700
Data Index: 185016 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.7736. Min Act: -0.1700
Data Index: 4762038 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.6174. Min Act: -0.1700
Data Index: 5599032 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.5861. Min Act: -0.1700
Data Index: 3571880 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.4611. Min Act: -0.1700
Data Index: 4762039 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.3986. Min Act: -0.1700
Data Index: 5133783 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.3674. Min Act: -0.1700
Data Index: 5625600 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.3986. Min Act: -0.1700
Data Index: 3313493 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.3049. Min Act: -0.1700
Data Index: 1472207 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.2424. Min Act: -0.1700
Data Index: 7394946 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.2424. Min Act: -0.1700
Data Index: 6424476 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.2111. Min Act: -0.1700
Data Index: 5015856 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.2111. Min Act: -0.1700
Data Index: 151671 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.1799. Min Act: -0.1700
Data Index: 4427385 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.1486. Min Act: -0.1700
Data Index: 1014088 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.1799. Min Act: -0.1700
Data Index: 6732638 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.1486. Min Act: -0.1700
Data Index: 2053406 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.1486. Min Act: -0.1700
Data Index: 7620626 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0236. Min Range: -7.0236
Max Act: 6.1486. Min Act: -0.1700
Data Index: 209424 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19