Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2202 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1595. Min Range: -8.1595
Max Act: 8.1595. Min Act: -0.1700
Data Index: 692366 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1595. Min Range: -8.1595
Max Act: 8.0970. Min Act: -0.1700
Data Index: 4621027 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1595. Min Range: -8.1595
Max Act: 8.0345. Min Act: -0.1700
Data Index: 5312459 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1595. Min Range: -8.1595
Max Act: 8.0345. Min Act: -0.1700
Data Index: 3625168 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.9720. Min Act: -0.1700
Data Index: 4127432 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.9095. Min Act: -0.1700
Data Index: 87479 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.8470. Min Act: -0.1700
Data Index: 7401673 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.8470. Min Act: -0.1700
Data Index: 489463 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 5219553 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.8470. Min Act: -0.1700
Data Index: 3032822 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.8470. Min Act: -0.1700
Data Index: 7462418 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 6911665 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 8718976 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 184454 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 822825 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 2244390 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7220. Min Act: -0.1700
Data Index: 4659539 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7845. Min Act: -0.1700
Data Index: 3811836 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7220. Min Act: -0.1700
Data Index: 1745505 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1595. Min Range: -8.1595
Max Act: 7.7220. Min Act: -0.1700
Data Index: 832737 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19