Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.6795. Min Act: -0.1700
Data Index: 5970807 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.5857. Min Act: -0.1700
Data Index: 5562858 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.5545. Min Act: -0.1700
Data Index: 4943884 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.5232. Min Act: -0.1700
Data Index: 4364445 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.5232. Min Act: -0.1700
Data Index: 4943885 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.5232. Min Act: -0.1700
Data Index: 7972085 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4920. Min Act: -0.1700
Data Index: 2533399 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4920. Min Act: -0.1700
Data Index: 7987215 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 3343258 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4607. Min Act: -0.1700
Data Index: 3617935 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 2389669 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 3364709 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 5923388 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 4224047 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.3670. Min Act: -0.1700
Data Index: 8656014 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.3982. Min Act: -0.1700
Data Index: 8198425 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 5211368 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.3982. Min Act: -0.1700
Data Index: 3387729 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.4295. Min Act: -0.1700
Data Index: 2626002 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6795. Min Range: -5.6795
Max Act: 5.3982. Min Act: -0.1700
Data Index: 5047555 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19