Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4315. Min Range: -7.4315
Max Act: 7.4315. Min Act: -0.1700
Data Index: 8454431 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4315. Min Range: -7.4315
Max Act: 7.1815. Min Act: -0.1700
Data Index: 3198118 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4315. Min Range: -7.4315
Max Act: 7.0878. Min Act: -0.1700
Data Index: 670037 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4315. Min Range: -7.4315
Max Act: 7.0565. Min Act: -0.1700
Data Index: 7114721 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4315. Min Range: -7.4315
Max Act: 7.0253. Min Act: -0.1700
Data Index: 5076324 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4315. Min Range: -7.4315
Max Act: 7.0565. Min Act: -0.1700
Data Index: 1797073 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.9940. Min Act: -0.1700
Data Index: 532346 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.9628. Min Act: -0.1700
Data Index: 2001022 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.9003. Min Act: -0.1700
Data Index: 926069 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.8690. Min Act: -0.1700
Data Index: 6951423 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.8690. Min Act: -0.1700
Data Index: 110225 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.8690. Min Act: -0.1700
Data Index: 7036209 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.8065. Min Act: -0.1700
Data Index: 7697276 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.8065. Min Act: -0.1700
Data Index: 3593809 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.8065. Min Act: -0.1700
Data Index: 1011594 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.7753. Min Act: -0.1700
Data Index: 4665265 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.7753. Min Act: -0.1700
Data Index: 8251799 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.7753. Min Act: -0.1700
Data Index: 1195370 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.7128. Min Act: -0.1700
Data Index: 3660015 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4315. Min Range: -7.4315
Max Act: 6.7128. Min Act: -0.1700
Data Index: 7100336 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19