Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0399. Min Range: -12.0399
Max Act: 12.0399. Min Act: -0.1700
Data Index: 5919916 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.6649. Min Act: -0.1700
Data Index: 850116 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.6649. Min Act: -0.1700
Data Index: 7926326 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.6024. Min Act: -0.1700
Data Index: 7859425 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.4774. Min Act: -0.1700
Data Index: 1765084 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.2899. Min Act: -0.1700
Data Index: 2787066 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.2899. Min Act: -0.1700
Data Index: 7227129 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.2899. Min Act: -0.1700
Data Index: 4700812 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.2274. Min Act: -0.1700
Data Index: 4895399 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.2274. Min Act: -0.1700
Data Index: 7289173 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.0399. Min Act: -0.1700
Data Index: 5879800 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.9774. Min Act: -0.1700
Data Index: 1471027 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.9149. Min Act: -0.1700
Data Index: 2161340 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0399. Min Range: -12.0399
Max Act: 11.0399. Min Act: -0.1700
Data Index: 1672652 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.9149. Min Act: -0.1700
Data Index: 3009202 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.9149. Min Act: -0.1700
Data Index: 6444979 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.8524. Min Act: -0.1700
Data Index: 6892498 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.8524. Min Act: -0.1700
Data Index: 73001 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.8524. Min Act: -0.1700
Data Index: 3048321 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0399. Min Range: -12.0399
Max Act: 10.8524. Min Act: -0.1700
Data Index: 3890491 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19