Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 1894081 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.8847. Min Act: -0.1700
Data Index: 188289 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.8535. Min Act: -0.1700
Data Index: 7373879 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4234745 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5960414 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6213543 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7597. Min Act: -0.1700
Data Index: 3893065 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 3871805 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7597. Min Act: -0.1700
Data Index: 2627658 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1012040 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1431773 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 5570370 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.6972. Min Act: -0.1700
Data Index: 262016 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 2563009 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 652919 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 3022449 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4383004 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4654501 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.7285. Min Act: -0.1700
Data Index: 4929968 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8847. Min Range: -5.8847
Max Act: 5.6972. Min Act: -0.1700
Data Index: 5291062 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19