Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4020 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.7720. Min Act: -0.1700
Data Index: 8767876 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.6468. Min Act: -0.1700
Data Index: 4091241 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.6155. Min Act: -0.1700
Data Index: 5818878 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5842. Min Act: -0.1700
Data Index: 6879422 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5842. Min Act: -0.1700
Data Index: 2707425 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.6155. Min Act: -0.1700
Data Index: 7220031 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5529. Min Act: -0.1700
Data Index: 3676453 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5529. Min Act: -0.1700
Data Index: 3503893 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5373. Min Act: -0.1700
Data Index: 3465903 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.5059. Min Act: -0.1700
Data Index: 2104471 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4746. Min Act: -0.1700
Data Index: 5580771 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4903. Min Act: -0.1700
Data Index: 3250656 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4746. Min Act: -0.1700
Data Index: 3399482 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4903. Min Act: -0.1700
Data Index: 4336581 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4589. Min Act: -0.1700
Data Index: 7641375 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4589. Min Act: -0.1700
Data Index: 8021780 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4746. Min Act: -0.1700
Data Index: 8503230 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4589. Min Act: -0.1700
Data Index: 8745163 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4433. Min Act: -0.1700
Data Index: 8021693 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7720. Min Range: -3.7720
Max Act: 3.4276. Min Act: -0.1700
Data Index: 6775462 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19