Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 336 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3231. Min Range: -6.3231
Max Act: 6.3231. Min Act: -0.1700
Data Index: 6724235 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3231. Min Range: -6.3231
Max Act: 6.0731. Min Act: -0.1700
Data Index: 150594 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3231. Min Range: -6.3231
Max Act: 6.0731. Min Act: -0.1700
Data Index: 5167206 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3231. Min Range: -6.3231
Max Act: 6.0106. Min Act: -0.1700
Data Index: 6785880 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.9481. Min Act: -0.1700
Data Index: 1862605 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.9168. Min Act: -0.1700
Data Index: 7929868 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.8856. Min Act: -0.1700
Data Index: 712587 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.8543. Min Act: -0.1700
Data Index: 6495694 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.8231. Min Act: -0.1700
Data Index: 3274839 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.7918. Min Act: -0.1700
Data Index: 2437150 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.7606. Min Act: -0.1700
Data Index: 6793100 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.7606. Min Act: -0.1700
Data Index: 2466781 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.6981. Min Act: -0.1700
Data Index: 289245 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.7293. Min Act: -0.1700
Data Index: 4773960 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.7606. Min Act: -0.1700
Data Index: 3792713 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.7293. Min Act: -0.1700
Data Index: 4277372 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.6981. Min Act: -0.1700
Data Index: 1139187 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.6981. Min Act: -0.1700
Data Index: 3799136 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.6981. Min Act: -0.1700
Data Index: 1121454 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3231. Min Range: -6.3231
Max Act: 5.6356. Min Act: -0.1700
Data Index: 6092576 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19