Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.9252. Min Act: -0.1700
Data Index: 5513016 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.9252. Min Act: -0.1700
Data Index: 1044755 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.7377. Min Act: -0.1700
Data Index: 183549 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.7377. Min Act: -0.1700
Data Index: 2287587 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.7377. Min Act: -0.1700
Data Index: 6145020 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.5815. Min Act: -0.1700
Data Index: 3435000 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.4877. Min Act: -0.1700
Data Index: 8640365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.4877. Min Act: -0.1700
Data Index: 2985077 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.4877. Min Act: -0.1700
Data Index: 4206073 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.4877. Min Act: -0.1700
Data Index: 5475452 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.4252. Min Act: -0.1700
Data Index: 5176250 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.4252. Min Act: -0.1700
Data Index: 8412847 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.3940. Min Act: -0.1700
Data Index: 1610397 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.3940. Min Act: -0.1700
Data Index: 8431159 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.3627. Min Act: -0.1700
Data Index: 8556544 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.3315. Min Act: -0.1700
Data Index: 2635142 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.3315. Min Act: -0.1700
Data Index: 79119 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.3315. Min Act: -0.1700
Data Index: 2683416 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.2690. Min Act: -0.1700
Data Index: 49669 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9252. Min Range: -7.9252
Max Act: 7.2690. Min Act: -0.1700
Data Index: 1090903 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19