Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4553 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.6242. Min Act: -0.1700
Data Index: 8035537 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.4679. Min Act: -0.1700
Data Index: 2468603 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.3742. Min Act: -0.1700
Data Index: 578015 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.2179. Min Act: -0.1700
Data Index: 888413 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.1867. Min Act: -0.1700
Data Index: 5541940 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.1554. Min Act: -0.1700
Data Index: 6656492 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0617. Min Act: -0.1700
Data Index: 8753759 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0929. Min Act: -0.1700
Data Index: 6624509 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0304. Min Act: -0.1700
Data Index: 3940727 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0617. Min Act: -0.1700
Data Index: 5870197 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0304. Min Act: -0.1700
Data Index: 2647895 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0304. Min Act: -0.1700
Data Index: 7543102 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9992. Min Act: -0.1700
Data Index: 3884785 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9679. Min Act: -0.1700
Data Index: 1315857 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9992. Min Act: -0.1700
Data Index: 5623448 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9992. Min Act: -0.1700
Data Index: 5219952 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6242. Min Range: -5.6242
Max Act: 5.0304. Min Act: -0.1700
Data Index: 8697577 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9679. Min Act: -0.1700
Data Index: 1989176 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9679. Min Act: -0.1700
Data Index: 2339472 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6242. Min Range: -5.6242
Max Act: 4.9679. Min Act: -0.1700
Data Index: 3940728 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19