Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4471 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.4296. Min Act: -0.1700
Data Index: 8011958 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2734. Min Act: -0.1700
Data Index: 3670114 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2109. Min Act: -0.1700
Data Index: 8630427 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2109. Min Act: -0.1700
Data Index: 3641711 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2109. Min Act: -0.1700
Data Index: 4774800 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.2109. Min Act: -0.1700
Data Index: 7597441 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1171. Min Act: -0.1700
Data Index: 3872058 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.1171. Min Act: -0.1700
Data Index: 8207026 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0859. Min Act: -0.1700
Data Index: 7778185 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0546. Min Act: -0.1700
Data Index: 6812396 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0546. Min Act: -0.1700
Data Index: 6656022 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0546. Min Act: -0.1700
Data Index: 4207124 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0233. Min Act: -0.1700
Data Index: 4416116 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0233. Min Act: -0.1700
Data Index: 7242595 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0233. Min Act: -0.1700
Data Index: 7872420 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0233. Min Act: -0.1700
Data Index: 7872386 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0233. Min Act: -0.1700
Data Index: 8661753 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4296. Min Range: -4.4296
Max Act: 4.0233. Min Act: -0.1700
Data Index: 2878530 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4296. Min Range: -4.4296
Max Act: 3.9921. Min Act: -0.1700
Data Index: 3825730 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4296. Min Range: -4.4296
Max Act: 3.9921. Min Act: -0.1700
Data Index: 2259928 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19