Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.5688. Min Act: -0.1700
Data Index: 3141955 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.5063. Min Act: -0.1700
Data Index: 3455073 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.4438. Min Act: -0.1700
Data Index: 7753756 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.4438. Min Act: -0.1700
Data Index: 6950688 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.3813. Min Act: -0.1700
Data Index: 6125086 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.3813. Min Act: -0.1700
Data Index: 4992988 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.3188. Min Act: -0.1700
Data Index: 7985582 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.2563. Min Act: -0.1700
Data Index: 4955433 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1938. Min Act: -0.1700
Data Index: 7245019 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 1717194 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1938. Min Act: -0.1700
Data Index: 4344301 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1938. Min Act: -0.1700
Data Index: 5338428 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 2459236 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 2006953 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 5984313 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 7645861 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 4015915 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 2597932 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.1313. Min Act: -0.1700
Data Index: 4989308 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5688. Min Range: -8.5688
Max Act: 8.0063. Min Act: -0.1700
Data Index: 3815728 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19