Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.7732. Min Act: -0.1700
Data Index: 3565576 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.7107. Min Act: -0.1700
Data Index: 4106949 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.6482. Min Act: -0.1700
Data Index: 3557566 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.5857. Min Act: -0.1700
Data Index: 1945639 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.5232. Min Act: -0.1700
Data Index: 4884487 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.5232. Min Act: -0.1700
Data Index: 4470033 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.5232. Min Act: -0.1700
Data Index: 3946263 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.3982. Min Act: -0.1700
Data Index: 7864869 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.3357. Min Act: -0.1700
Data Index: 8377827 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2732. Min Act: -0.1700
Data Index: 4094626 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2732. Min Act: -0.1700
Data Index: 7125482 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2732. Min Act: -0.1700
Data Index: 3046721 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2732. Min Act: -0.1700
Data Index: 5543878 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 1335691 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 16046 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 870775 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 7920077 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 655062 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 7318993 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7732. Min Range: -8.7732
Max Act: 8.2107. Min Act: -0.1700
Data Index: 8415674 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19