Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2061. Min Range: -5.2061
Max Act: 5.2061. Min Act: -0.1700
Data Index: 8619323 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2061. Min Range: -5.2061
Max Act: 5.1748. Min Act: -0.1700
Data Index: 7580869 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2061. Min Range: -5.2061
Max Act: 5.1436. Min Act: -0.1700
Data Index: 1175892 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2061. Min Range: -5.2061
Max Act: 5.1123. Min Act: -0.1700
Data Index: 8504193 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2061. Min Range: -5.2061
Max Act: 5.0498. Min Act: -0.1700
Data Index: 8171345 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2061. Min Range: -5.2061
Max Act: 5.0186. Min Act: -0.1700
Data Index: 6574500 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9873. Min Act: -0.1700
Data Index: 996458 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9561. Min Act: -0.1700
Data Index: 5981182 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9873. Min Act: -0.1700
Data Index: 8504194 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9873. Min Act: -0.1700
Data Index: 56013 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9561. Min Act: -0.1700
Data Index: 2029914 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9561. Min Act: -0.1700
Data Index: 1735698 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9561. Min Act: -0.1700
Data Index: 1749186 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9248. Min Act: -0.1700
Data Index: 1601266 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9248. Min Act: -0.1700
Data Index: 7405905 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.9248. Min Act: -0.1700
Data Index: 4104202 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.8936. Min Act: -0.1700
Data Index: 7277850 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.8936. Min Act: -0.1700
Data Index: 1296016 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.8936. Min Act: -0.1700
Data Index: 7687350 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2061. Min Range: -5.2061
Max Act: 4.8936. Min Act: -0.1700
Data Index: 974486 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19