Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1982. Min Range: -7.1982
Max Act: 7.1982. Min Act: -0.1700
Data Index: 5276368 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1982. Min Range: -7.1982
Max Act: 7.0732. Min Act: -0.1700
Data Index: 2773540 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1982. Min Range: -7.1982
Max Act: 7.0420. Min Act: -0.1700
Data Index: 2773884 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1982. Min Range: -7.1982
Max Act: 7.0420. Min Act: -0.1700
Data Index: 7134479 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1982. Min Range: -7.1982
Max Act: 7.0107. Min Act: -0.1700
Data Index: 1515153 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1982. Min Range: -7.1982
Max Act: 7.0107. Min Act: -0.1700
Data Index: 459330 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.9482. Min Act: -0.1700
Data Index: 1576091 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.9482. Min Act: -0.1700
Data Index: 395939 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.9170. Min Act: -0.1700
Data Index: 5757496 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.9170. Min Act: -0.1700
Data Index: 5833813 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.9170. Min Act: -0.1700
Data Index: 1723195 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8857. Min Act: -0.1700
Data Index: 5491407 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8857. Min Act: -0.1700
Data Index: 6006375 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8545. Min Act: -0.1700
Data Index: 5150452 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8545. Min Act: -0.1700
Data Index: 960998 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.7920. Min Act: -0.1700
Data Index: 7825136 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8232. Min Act: -0.1700
Data Index: 5445905 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8232. Min Act: -0.1700
Data Index: 8741574 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.8232. Min Act: -0.1700
Data Index: 6480369 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1982. Min Range: -7.1982
Max Act: 6.7920. Min Act: -0.1700
Data Index: 6857070 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19