Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.3391. Min Act: -0.1700
Data Index: 754787 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.2898. Min Act: -0.1700
Data Index: 7921560 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.2071. Min Act: -0.1700
Data Index: 7650521 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1905. Min Act: -0.1700
Data Index: 6405255 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1739. Min Act: -0.1700
Data Index: 4786698 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1573. Min Act: -0.1700
Data Index: 2816129 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1573. Min Act: -0.1700
Data Index: 4855215 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1406. Min Act: -0.1700
Data Index: 5540624 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1239. Min Act: -0.1700
Data Index: 5894705 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1072. Min Act: -0.1700
Data Index: 236524 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1239. Min Act: -0.1700
Data Index: 3027853 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1239. Min Act: -0.1700
Data Index: 5277751 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1072. Min Act: -0.1700
Data Index: 2685939 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1072. Min Act: -0.1700
Data Index: 3684334 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1239. Min Act: -0.1700
Data Index: 2345961 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1072. Min Act: -0.1700
Data Index: 5439451 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.1072. Min Act: -0.1700
Data Index: 8214719 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.0904. Min Act: -0.1700
Data Index: 48344 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.0904. Min Act: -0.1700
Data Index: 6785022 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3391. Min Range: -2.3391
Max Act: 2.0904. Min Act: -0.1700
Data Index: 6830386 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19