Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1828. Min Range: -5.1828
Max Act: 5.1828. Min Act: -0.1700
Data Index: 3186592 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1828. Min Range: -5.1828
Max Act: 5.1203. Min Act: -0.1700
Data Index: 2796965 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1828. Min Range: -5.1828
Max Act: 5.0265. Min Act: -0.1700
Data Index: 7183385 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.8390. Min Act: -0.1700
Data Index: 5477419 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.8078. Min Act: -0.1700
Data Index: 370111 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.7140. Min Act: -0.1700
Data Index: 4929689 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.7140. Min Act: -0.1700
Data Index: 5962438 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6828. Min Act: -0.1700
Data Index: 1082909 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6515. Min Act: -0.1700
Data Index: 8695107 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.7140. Min Act: -0.1700
Data Index: 4465815 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6828. Min Act: -0.1700
Data Index: 8043908 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6828. Min Act: -0.1700
Data Index: 4650486 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6515. Min Act: -0.1700
Data Index: 3047001 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6515. Min Act: -0.1700
Data Index: 426984 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6203. Min Act: -0.1700
Data Index: 5816798 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.6203. Min Act: -0.1700
Data Index: 3455710 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.5890. Min Act: -0.1700
Data Index: 6778535 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.5890. Min Act: -0.1700
Data Index: 1970533 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.5890. Min Act: -0.1700
Data Index: 6712355 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1828. Min Range: -5.1828
Max Act: 4.5890. Min Act: -0.1700
Data Index: 5024932 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19