Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.2857. Min Act: -0.1700
Data Index: 3001414 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.2545. Min Act: -0.1700
Data Index: 1712431 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.1607. Min Act: -0.1700
Data Index: 6312121 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0357. Min Act: -0.1700
Data Index: 738938 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 4029973 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2857. Min Range: -6.2857
Max Act: 6.0045. Min Act: -0.1700
Data Index: 2568132 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4383845 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9732. Min Act: -0.1700
Data Index: 5715951 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 3696886 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 6241088 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4557017 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 667538 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9420. Min Act: -0.1700
Data Index: 6730061 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.9107. Min Act: -0.1700
Data Index: 105849 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.8795. Min Act: -0.1700
Data Index: 4067336 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.8482. Min Act: -0.1700
Data Index: 8703505 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.8795. Min Act: -0.1700
Data Index: 6420537 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.8482. Min Act: -0.1700
Data Index: 7254641 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.8795. Min Act: -0.1700
Data Index: 2558746 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2857. Min Range: -6.2857
Max Act: 5.8482. Min Act: -0.1700
Data Index: 5013139 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19