Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1189 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1348. Min Range: -1.1348
Max Act: 1.1348. Min Act: -0.1696
Data Index: 3325669 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.9605. Min Act: -0.1699
Data Index: 1949950 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.9089. Min Act: -0.1635
Data Index: 2713643 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8239. Min Act: -0.1664
Data Index: 6674522 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8239. Min Act: -0.1142
Data Index: 397530 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8155. Min Act: -0.1353
Data Index: 863078 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8155. Min Act: -0.1700
Data Index: 2088059 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8155. Min Act: -0.1696
Data Index: 6821467 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8239. Min Act: -0.1696
Data Index: 254883 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8071. Min Act: -0.1700
Data Index: 4243162 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8239. Min Act: -0.1689
Data Index: 6462491 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7987. Min Act: -0.1697
Data Index: 379809 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8155. Min Act: -0.1700
Data Index: 5201561 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.8071. Min Act: -0.1687
Data Index: 1490386 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7987. Min Act: -0.1700
Data Index: 4359753 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7987. Min Act: -0.1698
Data Index: 3271097 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7819. Min Act: -0.1700
Data Index: 2988569 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7736. Min Act: -0.1699
Data Index: 3401410 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7653. Min Act: -0.1667
Data Index: 3632858 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1348. Min Range: -1.1348
Max Act: 0.7653. Min Act: -0.1698
Data Index: 7190892 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19