Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4976 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.5477. Min Act: -0.1700
Data Index: 5260471 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.4539. Min Act: -0.1700
Data Index: 1393981 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.4227. Min Act: -0.1700
Data Index: 2652152 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.4227. Min Act: -0.1700
Data Index: 4759698 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.2664. Min Act: -0.1700
Data Index: 611164 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.2039. Min Act: -0.1700
Data Index: 4522195 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.1727. Min Act: -0.1700
Data Index: 4720340 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.1727. Min Act: -0.1700
Data Index: 3361435 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.1727. Min Act: -0.1700
Data Index: 5743552 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.1414. Min Act: -0.1700
Data Index: 3232128 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.1102. Min Act: -0.1700
Data Index: 8394110 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.1102. Min Act: -0.1700
Data Index: 470990 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0789. Min Act: -0.1700
Data Index: 5256084 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0789. Min Act: -0.1700
Data Index: 1657514 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0476. Min Act: -0.1700
Data Index: 8409236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0789. Min Act: -0.1700
Data Index: 2541859 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0164. Min Act: -0.1700
Data Index: 6877366 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0476. Min Act: -0.1700
Data Index: 1526075 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0476. Min Act: -0.1700
Data Index: 7928588 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5477. Min Range: -4.5477
Max Act: 4.0164. Min Act: -0.1700
Data Index: 6553696 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19