Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.6676. Min Act: -0.1700
Data Index: 7890043 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.5426. Min Act: -0.1700
Data Index: 7232377 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.4488. Min Act: -0.1700
Data Index: 5510926 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.4488. Min Act: -0.1700
Data Index: 5556429 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3863. Min Act: -0.1700
Data Index: 5930238 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3863. Min Act: -0.1700
Data Index: 3852514 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3863. Min Act: -0.1700
Data Index: 6528533 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3551. Min Act: -0.1700
Data Index: 6718929 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3551. Min Act: -0.1700
Data Index: 2989685 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3551. Min Act: -0.1700
Data Index: 309138 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3238. Min Act: -0.1700
Data Index: 212616 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3238. Min Act: -0.1700
Data Index: 3946693 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.3238. Min Act: -0.1700
Data Index: 8182485 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2613. Min Act: -0.1700
Data Index: 4786627 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2613. Min Act: -0.1700
Data Index: 1581146 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2613. Min Act: -0.1700
Data Index: 1088631 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2613. Min Act: -0.1700
Data Index: 709022 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2613. Min Act: -0.1700
Data Index: 2510816 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2301. Min Act: -0.1700
Data Index: 6801146 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6676. Min Range: -6.6676
Max Act: 6.2301. Min Act: -0.1700
Data Index: 3866751 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19