Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.9429. Min Act: -0.1700
Data Index: 7014899 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.9117. Min Act: -0.1700
Data Index: 2097576 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.9117. Min Act: -0.1700
Data Index: 3911717 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.8179. Min Act: -0.1700
Data Index: 5336555 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.7867. Min Act: -0.1700
Data Index: 7014900 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.7867. Min Act: -0.1700
Data Index: 3495047 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.6617. Min Act: -0.1700
Data Index: 116855 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.6304. Min Act: -0.1700
Data Index: 4269439 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5679. Min Act: -0.1700
Data Index: 7283905 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5679. Min Act: -0.1700
Data Index: 2817570 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5679. Min Act: -0.1700
Data Index: 1501138 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5367. Min Act: -0.1700
Data Index: 1079772 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5367. Min Act: -0.1700
Data Index: 6123293 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5054. Min Act: -0.1700
Data Index: 2663173 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5054. Min Act: -0.1700
Data Index: 1977137 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.5054. Min Act: -0.1700
Data Index: 7415228 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.4429. Min Act: -0.1700
Data Index: 7040964 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.4429. Min Act: -0.1700
Data Index: 973650 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.4117. Min Act: -0.1700
Data Index: 2082998 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9429. Min Range: -5.9429
Max Act: 5.4117. Min Act: -0.1700
Data Index: 5363208 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19