Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.5308. Min Act: -0.1700
Data Index: 991207 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.3433. Min Act: -0.1700
Data Index: 1072330 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.3121. Min Act: -0.1700
Data Index: 3558954 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.2808. Min Act: -0.1700
Data Index: 4135456 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.2808. Min Act: -0.1700
Data Index: 3798783 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.2183. Min Act: -0.1700
Data Index: 462567 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.2496. Min Act: -0.1700
Data Index: 2236726 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.1871. Min Act: -0.1700
Data Index: 1744221 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.1871. Min Act: -0.1700
Data Index: 3391008 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.1871. Min Act: -0.1700
Data Index: 3650283 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.1246. Min Act: -0.1700
Data Index: 4050578 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.1246. Min Act: -0.1700
Data Index: 575903 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.0933. Min Act: -0.1700
Data Index: 6806195 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.0621. Min Act: -0.1700
Data Index: 4740495 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.1246. Min Act: -0.1700
Data Index: 136451 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.0933. Min Act: -0.1700
Data Index: 13401 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.0621. Min Act: -0.1700
Data Index: 3627045 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.0308. Min Act: -0.1700
Data Index: 899098 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5308. Min Range: -7.5308
Max Act: 7.0621. Min Act: -0.1700
Data Index: 348603 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5308. Min Range: -7.5308
Max Act: 6.9996. Min Act: -0.1700
Data Index: 3073632 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19