Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0885. Min Range: -5.0885
Max Act: 5.0885. Min Act: -0.1700
Data Index: 3494745 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0885. Min Range: -5.0885
Max Act: 5.0572. Min Act: -0.1700
Data Index: 5385496 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.9322. Min Act: -0.1700
Data Index: 5670508 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.9322. Min Act: -0.1700
Data Index: 7553255 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.9010. Min Act: -0.1700
Data Index: 962038 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.9322. Min Act: -0.1700
Data Index: 4076587 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8385. Min Act: -0.1700
Data Index: 4709727 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8385. Min Act: -0.1700
Data Index: 3494746 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8697. Min Act: -0.1700
Data Index: 6787799 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7200811 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8385. Min Act: -0.1700
Data Index: 8260318 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8385. Min Act: -0.1700
Data Index: 2457433 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8385. Min Act: -0.1700
Data Index: 7847180 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8385. Min Act: -0.1700
Data Index: 6449836 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8072. Min Act: -0.1700
Data Index: 3718611 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.7760. Min Act: -0.1700
Data Index: 44886 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.7760. Min Act: -0.1700
Data Index: 1430843 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.8072. Min Act: -0.1700
Data Index: 7967275 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.7760. Min Act: -0.1700
Data Index: 5380708 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0885. Min Range: -5.0885
Max Act: 4.7760. Min Act: -0.1700
Data Index: 2641362 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19