Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 637 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.8731. Min Act: -0.1700
Data Index: 1117300 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.8106. Min Act: -0.1700
Data Index: 5040737 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7793. Min Act: -0.1700
Data Index: 4990916 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.8106. Min Act: -0.1700
Data Index: 259076 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.8106. Min Act: -0.1700
Data Index: 4806583 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.8106. Min Act: -0.1700
Data Index: 5658548 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7793. Min Act: -0.1700
Data Index: 4294491 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 2092747 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.8106. Min Act: -0.1700
Data Index: 8441197 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 2149303 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 3592733 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 5226561 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7481. Min Act: -0.1700
Data Index: 7943341 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.6856. Min Act: -0.1700
Data Index: 587358 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7168. Min Act: -0.1700
Data Index: 3714073 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7168. Min Act: -0.1700
Data Index: 3714077 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.6856. Min Act: -0.1700
Data Index: 8075042 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7168. Min Act: -0.1700
Data Index: 4333257 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.6856. Min Act: -0.1700
Data Index: 713972 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8731. Min Range: -7.8731
Max Act: 7.7168. Min Act: -0.1700
Data Index: 7049004 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19