Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.6789. Min Act: -0.1700
Data Index: 536733 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.6476. Min Act: -0.1700
Data Index: 2880418 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.6164. Min Act: -0.1700
Data Index: 1882544 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5539. Min Act: -0.1700
Data Index: 7970501 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5851. Min Act: -0.1700
Data Index: 928853 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5539. Min Act: -0.1700
Data Index: 6902833 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5539. Min Act: -0.1700
Data Index: 1524414 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5539. Min Act: -0.1700
Data Index: 7113299 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5226. Min Act: -0.1700
Data Index: 2606714 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5226. Min Act: -0.1700
Data Index: 7010521 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5539. Min Act: -0.1700
Data Index: 8462436 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5226. Min Act: -0.1700
Data Index: 8254887 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4914. Min Act: -0.1700
Data Index: 7970873 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.5226. Min Act: -0.1700
Data Index: 2322164 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4914. Min Act: -0.1700
Data Index: 5776972 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4914. Min Act: -0.1700
Data Index: 4210741 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4601. Min Act: -0.1700
Data Index: 6517240 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4601. Min Act: -0.1700
Data Index: 1839263 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4914. Min Act: -0.1700
Data Index: 41780 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6789. Min Range: -4.6789
Max Act: 4.4601. Min Act: -0.1700
Data Index: 1962827 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19