Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.5325. Min Act: -0.1700
Data Index: 8508281 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.4700. Min Act: -0.1700
Data Index: 2154441 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.4075. Min Act: -0.1700
Data Index: 6391995 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.3450. Min Act: -0.1700
Data Index: 2834272 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.3450. Min Act: -0.1700
Data Index: 1875582 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.3450. Min Act: -0.1700
Data Index: 4582310 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.3138. Min Act: -0.1700
Data Index: 6518209 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.2825. Min Act: -0.1700
Data Index: 2431343 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.2200. Min Act: -0.1700
Data Index: 6110912 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.1888. Min Act: -0.1700
Data Index: 5335300 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.1575. Min Act: -0.1700
Data Index: 8280556 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.1263. Min Act: -0.1700
Data Index: 2249553 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0950. Min Act: -0.1700
Data Index: 7790320 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.1263. Min Act: -0.1700
Data Index: 4482105 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0638. Min Act: -0.1700
Data Index: 22886 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0638. Min Act: -0.1700
Data Index: 4634274 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0325. Min Act: -0.1700
Data Index: 8484364 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0013. Min Act: -0.1700
Data Index: 3355391 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0325. Min Act: -0.1700
Data Index: 3855670 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5325. Min Range: -6.5325
Max Act: 6.0013. Min Act: -0.1700
Data Index: 4069580 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19