Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.3011. Min Act: -0.1700
Data Index: 41041 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.2073. Min Act: -0.1700
Data Index: 1263116 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.2073. Min Act: -0.1700
Data Index: 1056852 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.1135. Min Act: -0.1700
Data Index: 2373626 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.1135. Min Act: -0.1700
Data Index: 8003931 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.1135. Min Act: -0.1700
Data Index: 4786001 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.1135. Min Act: -0.1700
Data Index: 4749767 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0823. Min Act: -0.1700
Data Index: 5110649 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0823. Min Act: -0.1700
Data Index: 6273576 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0823. Min Act: -0.1700
Data Index: 4068508 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0823. Min Act: -0.1700
Data Index: 2382943 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0510. Min Act: -0.1700
Data Index: 6537042 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0510. Min Act: -0.1700
Data Index: 5584640 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0198. Min Act: -0.1700
Data Index: 5636044 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0823. Min Act: -0.1700
Data Index: 3160945 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0198. Min Act: -0.1700
Data Index: 7360759 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0198. Min Act: -0.1700
Data Index: 7442438 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0198. Min Act: -0.1700
Data Index: 269572 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0198. Min Act: -0.1700
Data Index: 3241476 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3011. Min Range: -4.3011
Max Act: 4.0198. Min Act: -0.1700
Data Index: 6899797 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19