Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5874 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7770. Min Range: -6.7770
Max Act: 6.7770. Min Act: -0.1700
Data Index: 8353090 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7770. Min Range: -6.7770
Max Act: 6.3082. Min Act: -0.1700
Data Index: 5745300 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7770. Min Range: -6.7770
Max Act: 6.0270. Min Act: -0.1700
Data Index: 3015507 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.9957. Min Act: -0.1700
Data Index: 4029871 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.9957. Min Act: -0.1700
Data Index: 3461863 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.9645. Min Act: -0.1700
Data Index: 2197235 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.9645. Min Act: -0.1700
Data Index: 7141832 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.9020. Min Act: -0.1700
Data Index: 7994415 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.9020. Min Act: -0.1700
Data Index: 5870109 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.8707. Min Act: -0.1700
Data Index: 6243438 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.8395. Min Act: -0.1700
Data Index: 2124902 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 517857 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 8364402 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 4173812 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7770. Min Act: -0.1700
Data Index: 7035663 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7457. Min Act: -0.1700
Data Index: 335444 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7457. Min Act: -0.1700
Data Index: 226434 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7457. Min Act: -0.1700
Data Index: 7413971 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7145. Min Act: -0.1700
Data Index: 6914817 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7770. Min Range: -6.7770
Max Act: 5.7457. Min Act: -0.1700
Data Index: 5681676 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19