Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2759 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.7594. Min Act: -0.1700
Data Index: 1188949 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.6031. Min Act: -0.1699
Data Index: 8070934 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.5406. Min Act: -0.1694
Data Index: 4332332 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.5094. Min Act: -0.1659
Data Index: 5352551 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.5094. Min Act: -0.1280
Data Index: 1187412 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.4781. Min Act: -0.1694
Data Index: 8010002 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.4156. Min Act: -0.1699
Data Index: 1739841 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.4156. Min Act: -0.1688
Data Index: 4533509 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.3531. Min Act: -0.1700
Data Index: 347076 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.2906. Min Act: -0.1700
Data Index: 4234182 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.2594. Min Act: -0.1700
Data Index: 4678449 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.2281. Min Act: -0.1682
Data Index: 45383 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.2281. Min Act: -0.1700
Data Index: 3167420 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.2281. Min Act: -0.1681
Data Index: 1592849 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.2281. Min Act: -0.1700
Data Index: 4678448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.1969. Min Act: -0.1698
Data Index: 7800577 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.1969. Min Act: -0.1685
Data Index: 2181939 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.1656. Min Act: -0.1689
Data Index: 6595412 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.1656. Min Act: -0.1656
Data Index: 519242 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7594. Min Range: -6.7594
Max Act: 6.1656. Min Act: -0.1641
Data Index: 4050507 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19