Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.3885. Min Act: -0.1700
Data Index: 4748390 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.2635. Min Act: -0.1700
Data Index: 2026146 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.2010. Min Act: -0.1700
Data Index: 3198513 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.2010. Min Act: -0.1700
Data Index: 4628691 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.1072. Min Act: -0.1700
Data Index: 4628688 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.0760. Min Act: -0.1700
Data Index: 574374 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3885. Min Range: -8.3885
Max Act: 8.0135. Min Act: -0.1700
Data Index: 1135813 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.9822. Min Act: -0.1700
Data Index: 5491124 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.7947. Min Act: -0.1700
Data Index: 8000072 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.7635. Min Act: -0.1700
Data Index: 2758366 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6697. Min Act: -0.1700
Data Index: 2580613 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.7322. Min Act: -0.1700
Data Index: 5036144 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6697. Min Act: -0.1700
Data Index: 5406798 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6697. Min Act: -0.1700
Data Index: 6869463 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6385. Min Act: -0.1700
Data Index: 5287768 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6385. Min Act: -0.1700
Data Index: 1191420 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6072. Min Act: -0.1700
Data Index: 285369 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6072. Min Act: -0.1700
Data Index: 437338 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6072. Min Act: -0.1700
Data Index: 8045578 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3885. Min Range: -8.3885
Max Act: 7.6072. Min Act: -0.1700
Data Index: 8618224 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19