Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0875. Min Range: -5.0875
Max Act: 5.0875. Min Act: -0.1700
Data Index: 5808965 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0875. Min Range: -5.0875
Max Act: 5.0250. Min Act: -0.1700
Data Index: 4162557 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.9000. Min Act: -0.1700
Data Index: 5047869 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.8063. Min Act: -0.1700
Data Index: 16138 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7750. Min Act: -0.1700
Data Index: 3159588 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.8063. Min Act: -0.1700
Data Index: 6229970 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.8063. Min Act: -0.1700
Data Index: 3356670 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.8375. Min Act: -0.1700
Data Index: 8684138 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.8063. Min Act: -0.1700
Data Index: 2050574 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7750. Min Act: -0.1700
Data Index: 7765440 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7125. Min Act: -0.1700
Data Index: 1571289 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7750. Min Act: -0.1700
Data Index: 8055343 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7438. Min Act: -0.1700
Data Index: 1757515 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7438. Min Act: -0.1700
Data Index: 297098 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4800598 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4162558 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.6813. Min Act: -0.1700
Data Index: 627629 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6897007 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.7125. Min Act: -0.1700
Data Index: 5322830 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0875. Min Range: -5.0875
Max Act: 4.6500. Min Act: -0.1700
Data Index: 5561525 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19