Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.6992. Min Act: -0.1700
Data Index: 6918838 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.6367. Min Act: -0.1697
Data Index: 5088016 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.4492. Min Act: -0.1691
Data Index: 6856798 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.3867. Min Act: -0.1700
Data Index: 4555081 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.3242. Min Act: -0.1700
Data Index: 1071753 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.3242. Min Act: -0.1700
Data Index: 7399867 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.3867. Min Act: -0.1699
Data Index: 7680718 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.2617. Min Act: -0.1700
Data Index: 1052238 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.2617. Min Act: -0.1700
Data Index: 558743 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.2617. Min Act: -0.1699
Data Index: 8038725 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.1992. Min Act: -0.1694
Data Index: 8323837 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.1367. Min Act: -0.1700
Data Index: 2470524 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.1367. Min Act: -0.1690
Data Index: 4453855 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.1367. Min Act: -0.1694
Data Index: 6137527 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.1367. Min Act: -0.1700
Data Index: 4181301 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.0742. Min Act: -0.1698
Data Index: 8584628 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.0742. Min Act: -0.1699
Data Index: 7941062 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.0742. Min Act: -0.1692
Data Index: 309195 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.6992. Min Range: -13.6992
Max Act: 13.0742. Min Act: -0.1700
Data Index: 8320445 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.6992. Min Range: -13.6992
Max Act: 12.9492. Min Act: -0.1699
Data Index: 3094536 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19