Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.7812. Min Act: -0.1700
Data Index: 5376561 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6875. Min Act: -0.1700
Data Index: 1823259 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6250. Min Act: -0.1700
Data Index: 2930994 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6250. Min Act: -0.1700
Data Index: 2489227 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6250. Min Act: -0.1700
Data Index: 5299781 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5625. Min Act: -0.1700
Data Index: 578917 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5625. Min Act: -0.1700
Data Index: 894413 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5625. Min Act: -0.1700
Data Index: 2142190 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5937. Min Act: -0.1700
Data Index: 717147 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5937. Min Act: -0.1700
Data Index: 2432270 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5625. Min Act: -0.1700
Data Index: 2475827 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5312. Min Act: -0.1700
Data Index: 1605577 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5312. Min Act: -0.1700
Data Index: 7213803 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5000. Min Act: -0.1700
Data Index: 6542723 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7356596 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2826741 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 8654277 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6860842 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.4375. Min Act: -0.1700
Data Index: 3327799 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2598815 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19