Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.5216. Min Act: -0.1700
Data Index: 295496 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.4903. Min Act: -0.1700
Data Index: 7295748 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.4589. Min Act: -0.1700
Data Index: 4448964 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.4433. Min Act: -0.1700
Data Index: 591130 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.4276. Min Act: -0.1700
Data Index: 24384 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.4276. Min Act: -0.1700
Data Index: 5193932 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3962. Min Act: -0.1700
Data Index: 8714996 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3962. Min Act: -0.1700
Data Index: 4016647 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3806. Min Act: -0.1700
Data Index: 8043721 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3649. Min Act: -0.1700
Data Index: 8628865 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3335. Min Act: -0.1700
Data Index: 3455545 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3649. Min Act: -0.1700
Data Index: 4135718 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3492. Min Act: -0.1700
Data Index: 6127279 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3492. Min Act: -0.1700
Data Index: 6244121 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3335. Min Act: -0.1700
Data Index: 6256791 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3335. Min Act: -0.1700
Data Index: 7036224 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3178. Min Act: -0.1700
Data Index: 3306628 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3178. Min Act: -0.1700
Data Index: 3193658 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3021. Min Act: -0.1700
Data Index: 2967694 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5216. Min Range: -3.5216
Max Act: 3.3178. Min Act: -0.1700
Data Index: 5688865 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19