Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.7027. Min Act: -0.1700
Data Index: 7049709 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.7027. Min Act: -0.1700
Data Index: 2803911 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.6090. Min Act: -0.1700
Data Index: 238610 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.5777. Min Act: -0.1700
Data Index: 38538 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.5777. Min Act: -0.1700
Data Index: 2768445 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.5465. Min Act: -0.1700
Data Index: 1689439 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.5152. Min Act: -0.1700
Data Index: 3890142 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4840. Min Act: -0.1700
Data Index: 1226916 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4840. Min Act: -0.1700
Data Index: 7373956 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4840. Min Act: -0.1700
Data Index: 5279149 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4527. Min Act: -0.1700
Data Index: 6899053 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4214. Min Act: -0.1700
Data Index: 5368595 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4527. Min Act: -0.1700
Data Index: 5593834 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4214. Min Act: -0.1700
Data Index: 7527199 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.3902. Min Act: -0.1700
Data Index: 8702560 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4214. Min Act: -0.1700
Data Index: 3186461 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.4214. Min Act: -0.1700
Data Index: 5931336 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.3902. Min Act: -0.1700
Data Index: 1022985 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.3902. Min Act: -0.1700
Data Index: 3432150 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7027. Min Range: -4.7027
Max Act: 4.3902. Min Act: -0.1700
Data Index: 1518258 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19