Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5921 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.9433. Min Act: -0.1700
Data Index: 5926809 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.9093. Min Act: -0.1700
Data Index: 3955289 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8752. Min Act: -0.1700
Data Index: 4610157 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8581. Min Act: -0.1700
Data Index: 855830 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8409. Min Act: -0.1700
Data Index: 7209351 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8238. Min Act: -0.1700
Data Index: 4224608 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8066. Min Act: -0.1700
Data Index: 3556214 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7894. Min Act: -0.1700
Data Index: 5525087 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8066. Min Act: -0.1700
Data Index: 4831485 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7894. Min Act: -0.1700
Data Index: 8215648 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8238. Min Act: -0.1700
Data Index: 1530031 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.8066. Min Act: -0.1700
Data Index: 3666960 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7894. Min Act: -0.1700
Data Index: 3126724 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7894. Min Act: -0.1700
Data Index: 4567323 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7894. Min Act: -0.1700
Data Index: 3111509 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7894. Min Act: -0.1700
Data Index: 7189641 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7722. Min Act: -0.1700
Data Index: 4889800 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7722. Min Act: -0.1700
Data Index: 6423554 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7549. Min Act: -0.1700
Data Index: 5902127 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9433. Min Range: -1.9433
Max Act: 1.7722. Min Act: -0.1700
Data Index: 287915 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19