Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.3828. Min Act: -0.1700
Data Index: 5309072 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.3516. Min Act: -0.1700
Data Index: 4528198 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.3203. Min Act: -0.1700
Data Index: 4671948 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.2578. Min Act: -0.1700
Data Index: 4237778 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.0703. Min Act: -0.1700
Data Index: 7071915 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.1328. Min Act: -0.1700
Data Index: 4299859 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.0703. Min Act: -0.1700
Data Index: 402269 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.0703. Min Act: -0.1700
Data Index: 3166418 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.0703. Min Act: -0.1700
Data Index: 3195216 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.0391. Min Act: -0.1700
Data Index: 2035516 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3828. Min Range: -6.3828
Max Act: 6.0391. Min Act: -0.1700
Data Index: 2913077 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.9766. Min Act: -0.1700
Data Index: 8485765 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.9141. Min Act: -0.1700
Data Index: 1805157 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.9453. Min Act: -0.1700
Data Index: 7841025 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.9141. Min Act: -0.1700
Data Index: 4727146 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.8828. Min Act: -0.1700
Data Index: 2733562 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.9453. Min Act: -0.1700
Data Index: 2780660 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.8828. Min Act: -0.1700
Data Index: 682410 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.8828. Min Act: -0.1700
Data Index: 1937694 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3828. Min Range: -6.3828
Max Act: 5.8828. Min Act: -0.1700
Data Index: 5704680 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19