Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.9511. Min Act: -0.1700
Data Index: 8143287 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.9198. Min Act: -0.1700
Data Index: 4983723 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.6698. Min Act: -0.1700
Data Index: 5497232 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.6073. Min Act: -0.1700
Data Index: 5354150 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5448. Min Act: -0.1700
Data Index: 4589462 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.5448. Min Act: -0.1700
Data Index: 1600323 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4823. Min Act: -0.1700
Data Index: 3094240 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4823. Min Act: -0.1700
Data Index: 4006168 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4823. Min Act: -0.1700
Data Index: 7881514 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 5606318 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 1605443 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4511. Min Act: -0.1700
Data Index: 256894 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4198. Min Act: -0.1700
Data Index: 6734559 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4198. Min Act: -0.1700
Data Index: 6981068 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3783819 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.3886. Min Act: -0.1700
Data Index: 614308 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.3886. Min Act: -0.1700
Data Index: 5478820 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.3886. Min Act: -0.1700
Data Index: 7682917 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.3886. Min Act: -0.1700
Data Index: 3761944 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9511. Min Range: -6.9511
Max Act: 6.3573. Min Act: -0.1700
Data Index: 5842665 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19