Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5280 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.7303. Min Act: -0.1700
Data Index: 7023610 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.6053. Min Act: -0.1700
Data Index: 6831840 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.5428. Min Act: -0.1700
Data Index: 7726718 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.4178. Min Act: -0.1700
Data Index: 8390174 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.3553. Min Act: -0.1700
Data Index: 4917122 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.3241. Min Act: -0.1700
Data Index: 7736693 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.3241. Min Act: -0.1700
Data Index: 6250139 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.2616. Min Act: -0.1700
Data Index: 528905 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.1991. Min Act: -0.1700
Data Index: 1889946 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.1991. Min Act: -0.1700
Data Index: 6120231 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.1678. Min Act: -0.1700
Data Index: 5975944 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.1366. Min Act: -0.1700
Data Index: 968323 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.1053. Min Act: -0.1700
Data Index: 2863513 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.1053. Min Act: -0.1700
Data Index: 4801039 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.0428. Min Act: -0.1700
Data Index: 6284683 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.0741. Min Act: -0.1700
Data Index: 3141885 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.0116. Min Act: -0.1700
Data Index: 5049002 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.0116. Min Act: -0.1700
Data Index: 6250141 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.0116. Min Act: -0.1700
Data Index: 3503817 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7303. Min Range: -6.7303
Max Act: 6.0116. Min Act: -0.1700
Data Index: 4889784 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19