Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.4961. Min Act: -0.1700
Data Index: 2145651 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.4023. Min Act: -0.1700
Data Index: 8398977 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.3086. Min Act: -0.1700
Data Index: 2145649 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.3086. Min Act: -0.1700
Data Index: 6069016 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.2148. Min Act: -0.1700
Data Index: 8817874 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.1523. Min Act: -0.1700
Data Index: 3177615 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.1836. Min Act: -0.1700
Data Index: 2786013 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.1211. Min Act: -0.1700
Data Index: 7942532 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.1211. Min Act: -0.1700
Data Index: 7942534 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.1211. Min Act: -0.1700
Data Index: 6918830 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0898. Min Act: -0.1700
Data Index: 7060207 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0898. Min Act: -0.1700
Data Index: 7942533 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.1211. Min Act: -0.1700
Data Index: 6834873 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0898. Min Act: -0.1700
Data Index: 7996012 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0898. Min Act: -0.1700
Data Index: 3430009 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0586. Min Act: -0.1700
Data Index: 3417291 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0586. Min Act: -0.1700
Data Index: 7559859 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0586. Min Act: -0.1700
Data Index: 2113836 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0273. Min Act: -0.1700
Data Index: 6641627 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4961. Min Range: -5.4961
Max Act: 5.0273. Min Act: -0.1700
Data Index: 3531 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19