Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4621 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.9231. Min Act: -0.1700
Data Index: 1766461 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.6731. Min Act: -0.1700
Data Index: 8162249 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.7044. Min Act: -0.1700
Data Index: 3538607 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.5169. Min Act: -0.1700
Data Index: 8209988 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.5481. Min Act: -0.1700
Data Index: 527760 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4856. Min Act: -0.1700
Data Index: 7427926 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4856. Min Act: -0.1700
Data Index: 110543 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4544. Min Act: -0.1700
Data Index: 3449832 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4231. Min Act: -0.1700
Data Index: 3832556 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4231. Min Act: -0.1700
Data Index: 4684686 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4544. Min Act: -0.1700
Data Index: 8176307 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.4544. Min Act: -0.1700
Data Index: 837169 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.3919. Min Act: -0.1700
Data Index: 5578053 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.3606. Min Act: -0.1700
Data Index: 1968847 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.3294. Min Act: -0.1700
Data Index: 5383547 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.3294. Min Act: -0.1700
Data Index: 2154660 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.2981. Min Act: -0.1700
Data Index: 5558006 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.2981. Min Act: -0.1700
Data Index: 6919934 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.2981. Min Act: -0.1700
Data Index: 5714424 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9231. Min Range: -7.9231
Max Act: 7.2981. Min Act: -0.1700
Data Index: 2897092 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19