Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.6380. Min Act: -0.1700
Data Index: 124348 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.6692. Min Act: -0.1700
Data Index: 6288571 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.5442. Min Act: -0.1700
Data Index: 8103107 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.4192. Min Act: -0.1700
Data Index: 7730529 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.3255. Min Act: -0.1700
Data Index: 2837788 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.3567. Min Act: -0.1700
Data Index: 4889018 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.3255. Min Act: -0.1700
Data Index: 7040908 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.3255. Min Act: -0.1700
Data Index: 4401562 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2942. Min Act: -0.1700
Data Index: 4662044 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2942. Min Act: -0.1700
Data Index: 537662 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2630. Min Act: -0.1700
Data Index: 8309433 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2317. Min Act: -0.1700
Data Index: 8049555 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2005. Min Act: -0.1700
Data Index: 8335720 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2005. Min Act: -0.1700
Data Index: 2396374 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2005. Min Act: -0.1700
Data Index: 739999 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2005. Min Act: -0.1700
Data Index: 1770316 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2005. Min Act: -0.1700
Data Index: 3686208 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.2005. Min Act: -0.1700
Data Index: 4137392 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.1692. Min Act: -0.1700
Data Index: 6725428 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6692. Min Range: -7.6692
Max Act: 7.1380. Min Act: -0.1700
Data Index: 1458162 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19