Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0176. Min Range: -6.0176
Max Act: 6.0176. Min Act: -0.1700
Data Index: 7321974 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.9551. Min Act: -0.1700
Data Index: 3030518 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.9551. Min Act: -0.1700
Data Index: 2481597 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.9238. Min Act: -0.1700
Data Index: 4444971 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 6379233 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 237065 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 2704143 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8613. Min Act: -0.1700
Data Index: 7181905 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 8765646 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8613. Min Act: -0.1700
Data Index: 7760564 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 5845017 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2286152 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 757168 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 3516457 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.7988. Min Act: -0.1700
Data Index: 1095959 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 4173794 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 1733968 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 455431 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8301. Min Act: -0.1700
Data Index: 2231480 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.7676. Min Act: -0.1700
Data Index: 6463861 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19