Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0063. Min Range: -6.0063
Max Act: 6.0063. Min Act: -0.1700
Data Index: 422063 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0063. Min Range: -6.0063
Max Act: 6.0063. Min Act: -0.1700
Data Index: 1521291 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.8500. Min Act: -0.1700
Data Index: 6199513 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.7250. Min Act: -0.1700
Data Index: 2558649 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6938. Min Act: -0.1700
Data Index: 3143258 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 3831479 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 5507503 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 2654017 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 2490903 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 7138899 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 6606747 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 3342574 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 3240450 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6625. Min Act: -0.1700
Data Index: 5024699 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6000. Min Act: -0.1700
Data Index: 2993438 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.5688. Min Act: -0.1700
Data Index: 56209 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.6313. Min Act: -0.1700
Data Index: 1073472 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.5688. Min Act: -0.1700
Data Index: 7070103 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.5688. Min Act: -0.1700
Data Index: 3105037 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0063. Min Range: -6.0063
Max Act: 5.5375. Min Act: -0.1700
Data Index: 5280272 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19