Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.6718. Min Act: -0.1700
Data Index: 2716784 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.6093. Min Act: -0.1700
Data Index: 1200650 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.6405. Min Act: -0.1700
Data Index: 4854225 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.6405. Min Act: -0.1700
Data Index: 1537253 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.6093. Min Act: -0.1700
Data Index: 5072943 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5780. Min Act: -0.1700
Data Index: 866991 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5780. Min Act: -0.1700
Data Index: 1437584 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5780. Min Act: -0.1700
Data Index: 4118572 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5780. Min Act: -0.1700
Data Index: 341975 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5780. Min Act: -0.1700
Data Index: 7396124 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5468. Min Act: -0.1700
Data Index: 4518072 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5780. Min Act: -0.1700
Data Index: 8482071 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5468. Min Act: -0.1700
Data Index: 4066242 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5155. Min Act: -0.1700
Data Index: 7879728 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5155. Min Act: -0.1700
Data Index: 4156175 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5155. Min Act: -0.1700
Data Index: 1875877 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5155. Min Act: -0.1700
Data Index: 1960227 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.5155. Min Act: -0.1700
Data Index: 886188 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.4843. Min Act: -0.1700
Data Index: 291863 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6718. Min Range: -6.6718
Max Act: 6.4843. Min Act: -0.1700
Data Index: 7256458 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19