Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.9449. Min Act: -0.1700
Data Index: 1469657 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.7574. Min Act: -0.1700
Data Index: 8415998 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.6636. Min Act: -0.1700
Data Index: 608522 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.4761. Min Act: -0.1700
Data Index: 2583154 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.3824. Min Act: -0.1700
Data Index: 2499345 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.3824. Min Act: -0.1700
Data Index: 2966204 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.3824. Min Act: -0.1700
Data Index: 8158403 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2886. Min Act: -0.1700
Data Index: 2654505 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2261. Min Act: -0.1700
Data Index: 451214 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2261. Min Act: -0.1700
Data Index: 1499488 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2261. Min Act: -0.1700
Data Index: 4105485 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2261. Min Act: -0.1700
Data Index: 215367 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2261. Min Act: -0.1700
Data Index: 2495455 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.2574. Min Act: -0.1700
Data Index: 2082619 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.1949. Min Act: -0.1700
Data Index: 6287957 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.1949. Min Act: -0.1700
Data Index: 1947105 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.1636. Min Act: -0.1700
Data Index: 2982686 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.1636. Min Act: -0.1700
Data Index: 1492604 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.1636. Min Act: -0.1700
Data Index: 2597191 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9449. Min Range: -7.9449
Max Act: 7.1636. Min Act: -0.1700
Data Index: 8487822 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19