Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.9428. Min Act: -0.1700
Data Index: 3403743 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.8178. Min Act: -0.1700
Data Index: 6676579 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.8178. Min Act: -0.1700
Data Index: 7524351 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.7553. Min Act: -0.1700
Data Index: 1722638 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.7241. Min Act: -0.1700
Data Index: 4241877 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.7241. Min Act: -0.1700
Data Index: 7883808 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.7241. Min Act: -0.1700
Data Index: 4959974 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.6616. Min Act: -0.1700
Data Index: 7530640 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.6616. Min Act: -0.1700
Data Index: 1940288 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.6928. Min Act: -0.1700
Data Index: 8408658 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5366. Min Act: -0.1700
Data Index: 3147237 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5678. Min Act: -0.1700
Data Index: 7444362 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5366. Min Act: -0.1700
Data Index: 7856091 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5053. Min Act: -0.1700
Data Index: 3555816 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5053. Min Act: -0.1700
Data Index: 3050584 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5053. Min Act: -0.1700
Data Index: 8212295 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5053. Min Act: -0.1700
Data Index: 1369214 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.5053. Min Act: -0.1700
Data Index: 416522 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.4428. Min Act: -0.1700
Data Index: 2843723 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9428. Min Range: -5.9428
Max Act: 5.4741. Min Act: -0.1700
Data Index: 3807471 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19