Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.8473. Min Act: -0.1700
Data Index: 5557723 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.7379. Min Act: -0.1700
Data Index: 2615438 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.7222. Min Act: -0.1700
Data Index: 3678587 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.6909. Min Act: -0.1700
Data Index: 3770188 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.6753. Min Act: -0.1700
Data Index: 6612190 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.6597. Min Act: -0.1700
Data Index: 4956465 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.6127. Min Act: -0.1700
Data Index: 2224784 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5971. Min Act: -0.1700
Data Index: 8520017 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5971. Min Act: -0.1700
Data Index: 1652591 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5657. Min Act: -0.1700
Data Index: 8180411 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5657. Min Act: -0.1700
Data Index: 3543657 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5501. Min Act: -0.1700
Data Index: 2012819 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5344. Min Act: -0.1700
Data Index: 2996541 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5344. Min Act: -0.1700
Data Index: 6325190 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5501. Min Act: -0.1700
Data Index: 6362863 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5344. Min Act: -0.1700
Data Index: 416475 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5188. Min Act: -0.1700
Data Index: 2494084 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5344. Min Act: -0.1700
Data Index: 7914566 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5188. Min Act: -0.1700
Data Index: 3602887 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8473. Min Range: -3.8473
Max Act: 3.5188. Min Act: -0.1700
Data Index: 421787 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19