Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.2534. Min Act: -0.1700
Data Index: 3941868 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.2534. Min Act: -0.1700
Data Index: 1896838 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.2222. Min Act: -0.1698
Data Index: 8354391 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.2222. Min Act: -0.1700
Data Index: 6433576 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.1909. Min Act: -0.1700
Data Index: 2777929 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.1909. Min Act: -0.1700
Data Index: 6399922 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.1909. Min Act: -0.1700
Data Index: 2217846 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.1909. Min Act: -0.1700
Data Index: 806366 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.1284. Min Act: -0.1700
Data Index: 1501577 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0659. Min Act: -0.1700
Data Index: 2553185 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0972. Min Act: -0.1700
Data Index: 5735599 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0972. Min Act: -0.1700
Data Index: 4725392 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0972. Min Act: -0.1700
Data Index: 6946442 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0347. Min Act: -0.1700
Data Index: 296446 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0659. Min Act: -0.1700
Data Index: 2408230 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0347. Min Act: -0.1700
Data Index: 1931110 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0347. Min Act: -0.1700
Data Index: 574955 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0347. Min Act: -0.1700
Data Index: 6238014 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0034. Min Act: -0.1700
Data Index: 5805690 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2534. Min Range: -6.2534
Max Act: 6.0034. Min Act: -0.1700
Data Index: 309616 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19