Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.4513. Min Act: -0.1700
Data Index: 4509627 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.4513. Min Act: -0.1700
Data Index: 8017806 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.3632. Min Act: -0.1700
Data Index: 8215482 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.3279. Min Act: -0.1700
Data Index: 5200022 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.3103. Min Act: -0.1700
Data Index: 2098208 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2927. Min Act: -0.1693
Data Index: 79096 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2750. Min Act: -0.1700
Data Index: 7482132 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2574. Min Act: -0.1697
Data Index: 6628642 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2574. Min Act: -0.1700
Data Index: 65788 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2574. Min Act: -0.1700
Data Index: 1755876 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2574. Min Act: -0.1698
Data Index: 700281 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2398. Min Act: -0.1700
Data Index: 5169669 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.2221. Min Act: -0.1699
Data Index: 2077513 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1869. Min Act: -0.1614
Data Index: 989745 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1869. Min Act: -0.1700
Data Index: 134305 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1869. Min Act: -0.1690
Data Index: 1552328 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1869. Min Act: -0.1700
Data Index: 4472805 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1693. Min Act: -0.1694
Data Index: 4220739 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1869. Min Act: -0.1663
Data Index: 7259585 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4513. Min Range: -1.4513
Max Act: 1.1693. Min Act: -0.1696
Data Index: 5958351 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19