Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2144 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.6421. Min Act: -0.1700
Data Index: 7287327 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.5484. Min Act: -0.1700
Data Index: 5944382 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.4546. Min Act: -0.1700
Data Index: 6566589 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.4234. Min Act: -0.1700
Data Index: 1252228 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1217659 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.3296. Min Act: -0.1700
Data Index: 6697885 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2984. Min Act: -0.1700
Data Index: 4959455 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.3296. Min Act: -0.1700
Data Index: 3303512 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2984. Min Act: -0.1700
Data Index: 2769406 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2984. Min Act: -0.1700
Data Index: 6316587 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2984. Min Act: -0.1700
Data Index: 7227590 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2671. Min Act: -0.1700
Data Index: 5968416 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2671. Min Act: -0.1700
Data Index: 7863171 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2671. Min Act: -0.1700
Data Index: 8109920 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2359. Min Act: -0.1700
Data Index: 6751454 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2359. Min Act: -0.1700
Data Index: 6748446 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2046. Min Act: -0.1700
Data Index: 7744768 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.2046. Min Act: -0.1700
Data Index: 8104450 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.1734. Min Act: -0.1700
Data Index: 2250606 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6421. Min Range: -4.6421
Max Act: 4.1734. Min Act: -0.1700
Data Index: 7027716 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19