Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.9589. Min Act: -0.1700
Data Index: 4631587 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.6464. Min Act: -0.1700
Data Index: 6944951 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.5839. Min Act: -0.1700
Data Index: 8372040 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.5527. Min Act: -0.1700
Data Index: 6801710 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.4902. Min Act: -0.1700
Data Index: 6228969 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.4589. Min Act: -0.1700
Data Index: 8164476 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.4589. Min Act: -0.1700
Data Index: 5958996 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.3964. Min Act: -0.1700
Data Index: 929248 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 4074391 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.3652. Min Act: -0.1700
Data Index: 7535524 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.3027. Min Act: -0.1700
Data Index: 6194692 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.2714. Min Act: -0.1700
Data Index: 6162343 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.2714. Min Act: -0.1700
Data Index: 1231127 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.2714. Min Act: -0.1700
Data Index: 5338596 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.2714. Min Act: -0.1700
Data Index: 2003889 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.2402. Min Act: -0.1700
Data Index: 4224244 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.2089. Min Act: -0.1700
Data Index: 683839 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.1777. Min Act: -0.1700
Data Index: 4482392 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.1777. Min Act: -0.1700
Data Index: 7138605 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9589. Min Range: -4.9589
Max Act: 4.1777. Min Act: -0.1700
Data Index: 3447334 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19