Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.4426. Min Act: -0.1700
Data Index: 7834732 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.3801. Min Act: -0.1700
Data Index: 5264232 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.3488. Min Act: -0.1700
Data Index: 4467895 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.3488. Min Act: -0.1700
Data Index: 5609262 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2409107 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.2863. Min Act: -0.1700
Data Index: 7030985 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.2551. Min Act: -0.1700
Data Index: 1953690 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.2238. Min Act: -0.1700
Data Index: 3976423 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1926. Min Act: -0.1700
Data Index: 5827563 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.2238. Min Act: -0.1700
Data Index: 8041013 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1926. Min Act: -0.1700
Data Index: 2724643 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1926. Min Act: -0.1700
Data Index: 4830957 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1613. Min Act: -0.1700
Data Index: 6851007 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1301. Min Act: -0.1700
Data Index: 5224459 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1301. Min Act: -0.1700
Data Index: 2343541 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1301. Min Act: -0.1700
Data Index: 476568 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.1301. Min Act: -0.1700
Data Index: 2633538 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.0988. Min Act: -0.1700
Data Index: 3634942 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.0988. Min Act: -0.1700
Data Index: 8213731 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4426. Min Range: -5.4426
Max Act: 5.0363. Min Act: -0.1700
Data Index: 3539402 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19