Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1856 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.9495. Min Act: -0.1700
Data Index: 4945101 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.9495. Min Act: -0.1700
Data Index: 3454795 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.8557. Min Act: -0.1700
Data Index: 801297 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.8245. Min Act: -0.1700
Data Index: 1976699 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.6682. Min Act: -0.1700
Data Index: 8223482 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.6370. Min Act: -0.1700
Data Index: 862604 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.6370. Min Act: -0.1700
Data Index: 3181951 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.6057. Min Act: -0.1700
Data Index: 1155363 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5432. Min Act: -0.1700
Data Index: 6952218 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5432. Min Act: -0.1700
Data Index: 6865502 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5120. Min Act: -0.1700
Data Index: 6191315 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5745. Min Act: -0.1700
Data Index: 797599 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5120. Min Act: -0.1700
Data Index: 8802798 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5120. Min Act: -0.1700
Data Index: 4131017 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5432. Min Act: -0.1700
Data Index: 565502 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5432. Min Act: -0.1700
Data Index: 7609640 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5120. Min Act: -0.1700
Data Index: 6686921 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.4807. Min Act: -0.1700
Data Index: 4473823 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.5120. Min Act: -0.1700
Data Index: 3546320 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9495. Min Range: -6.9495
Max Act: 6.4807. Min Act: -0.1700
Data Index: 1445647 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19