Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1222 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0954. Min Act: -0.1700
Data Index: 1901815 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0642. Min Act: -0.1700
Data Index: 7614190 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0954. Min Act: -0.1700
Data Index: 1628737 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0954. Min Act: -0.1700
Data Index: 5118325 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0642. Min Act: -0.1700
Data Index: 7201228 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0642. Min Act: -0.1700
Data Index: 1361582 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0642. Min Act: -0.1700
Data Index: 3274067 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0642. Min Act: -0.1700
Data Index: 2673113 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0329. Min Act: -0.1700
Data Index: 474659 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0329. Min Act: -0.1700
Data Index: 7204621 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0329. Min Act: -0.1700
Data Index: 4521239 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0329. Min Act: -0.1700
Data Index: 5649155 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0329. Min Act: -0.1700
Data Index: 6343495 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0329. Min Act: -0.1700
Data Index: 2116928 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0954. Min Range: -5.0954
Max Act: 4.9704. Min Act: -0.1700
Data Index: 7418284 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0954. Min Range: -5.0954
Max Act: 4.9704. Min Act: -0.1700
Data Index: 1633796 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0017. Min Act: -0.1700
Data Index: 2231672 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0017. Min Act: -0.1700
Data Index: 5897461 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0954. Min Range: -5.0954
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4692851 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0954. Min Range: -5.0954
Max Act: 4.9392. Min Act: -0.1700
Data Index: 6953120 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19