Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5572 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.3681. Min Act: -0.1700
Data Index: 4677409 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.2431. Min Act: -0.1700
Data Index: 6101864 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.2119. Min Act: -0.1700
Data Index: 3259618 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.1806. Min Act: -0.1700
Data Index: 6026083 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.1806. Min Act: -0.1700
Data Index: 99130 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.1806. Min Act: -0.1700
Data Index: 4582440 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.0869. Min Act: -0.1700
Data Index: 2214358 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3681. Min Range: -7.3681
Max Act: 7.0244. Min Act: -0.1700
Data Index: 592729 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.9619. Min Act: -0.1700
Data Index: 533374 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.8994. Min Act: -0.1700
Data Index: 1194345 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.8369. Min Act: -0.1700
Data Index: 4431118 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.8369. Min Act: -0.1700
Data Index: 3434479 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.8056. Min Act: -0.1700
Data Index: 5064829 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.8369. Min Act: -0.1700
Data Index: 3729057 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.7744. Min Act: -0.1700
Data Index: 7422412 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.8056. Min Act: -0.1700
Data Index: 4006809 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.7431. Min Act: -0.1700
Data Index: 8102486 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.7119. Min Act: -0.1700
Data Index: 5542080 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.7119. Min Act: -0.1700
Data Index: 10778 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3681. Min Range: -7.3681
Max Act: 6.7119. Min Act: -0.1700
Data Index: 4077838 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19