Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.8723. Min Act: -0.1700
Data Index: 445892 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.8411. Min Act: -0.1700
Data Index: 3993512 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.8411. Min Act: -0.1700
Data Index: 598032 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.8098. Min Act: -0.1700
Data Index: 5757248 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7473. Min Act: -0.1700
Data Index: 489780 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7786. Min Act: -0.1700
Data Index: 188126 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7473. Min Act: -0.1700
Data Index: 1837069 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7473. Min Act: -0.1700
Data Index: 4825964 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7161. Min Act: -0.1700
Data Index: 8084070 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7058705 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 4219337 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1311994 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7161. Min Act: -0.1700
Data Index: 4645515 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 2938882 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 7045931 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 7760313 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 190078 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 3567452 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 2311760 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 7830444 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19