Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.3738. Min Act: -0.1700
Data Index: 583588 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.3426. Min Act: -0.1700
Data Index: 6790848 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.3113. Min Act: -0.1700
Data Index: 6665246 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.3113. Min Act: -0.1700
Data Index: 5582382 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.2801. Min Act: -0.1700
Data Index: 6365991 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.2488. Min Act: -0.1700
Data Index: 7001035 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.2176. Min Act: -0.1700
Data Index: 7429802 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.1863. Min Act: -0.1700
Data Index: 1379340 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.1238. Min Act: -0.1700
Data Index: 8243025 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.1238. Min Act: -0.1700
Data Index: 6006729 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.1238. Min Act: -0.1700
Data Index: 729922 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.1238. Min Act: -0.1700
Data Index: 1804457 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0926. Min Act: -0.1700
Data Index: 4876215 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0926. Min Act: -0.1700
Data Index: 1029360 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0926. Min Act: -0.1700
Data Index: 5611633 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0926. Min Act: -0.1700
Data Index: 1649806 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0613. Min Act: -0.1700
Data Index: 593021 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0301. Min Act: -0.1700
Data Index: 896233 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3738. Min Range: -5.3738
Max Act: 5.0301. Min Act: -0.1700
Data Index: 5077759 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3738. Min Range: -5.3738
Max Act: 4.9676. Min Act: -0.1700
Data Index: 2058326 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19