Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.4201. Min Act: -0.1700
Data Index: 3007153 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.3576. Min Act: -0.1700
Data Index: 6213774 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.3576. Min Act: -0.1700
Data Index: 6143496 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.2951. Min Act: -0.1700
Data Index: 3490222 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.2639. Min Act: -0.1700
Data Index: 2337159 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.2639. Min Act: -0.1700
Data Index: 3771417 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.2014. Min Act: -0.1700
Data Index: 5419145 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1701. Min Act: -0.1700
Data Index: 6816112 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1389. Min Act: -0.1700
Data Index: 5728636 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1701. Min Act: -0.1700
Data Index: 932256 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1076. Min Act: -0.1700
Data Index: 1482262 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1076. Min Act: -0.1700
Data Index: 1854886 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1389. Min Act: -0.1700
Data Index: 4435666 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1389. Min Act: -0.1700
Data Index: 6229390 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1389. Min Act: -0.1700
Data Index: 7250171 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.2014. Min Act: -0.1700
Data Index: 7552484 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1076. Min Act: -0.1700
Data Index: 5183788 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.0764. Min Act: -0.1700
Data Index: 7254413 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.0764. Min Act: -0.1700
Data Index: 4620525 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4201. Min Range: -8.4201
Max Act: 8.1076. Min Act: -0.1700
Data Index: 4602698 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19