Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 681 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1744. Min Range: -7.1744
Max Act: 7.1432. Min Act: -0.1700
Data Index: 6484273 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1744. Min Range: -7.1744
Max Act: 7.1744. Min Act: -0.1700
Data Index: 6987883 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1744. Min Range: -7.1744
Max Act: 7.1432. Min Act: -0.1700
Data Index: 7416925 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1744. Min Range: -7.1744
Max Act: 7.0807. Min Act: -0.1700
Data Index: 469030 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1744. Min Range: -7.1744
Max Act: 7.0182. Min Act: -0.1700
Data Index: 4203314 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.9869. Min Act: -0.1700
Data Index: 8648089 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.8932. Min Act: -0.1700
Data Index: 2068822 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.8619. Min Act: -0.1700
Data Index: 7180865 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.8932. Min Act: -0.1700
Data Index: 642417 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.7682. Min Act: -0.1700
Data Index: 2409563 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.7682. Min Act: -0.1700
Data Index: 4493800 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.7682. Min Act: -0.1700
Data Index: 6348723 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.7057. Min Act: -0.1700
Data Index: 5282672 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.7057. Min Act: -0.1700
Data Index: 6615921 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.6744. Min Act: -0.1700
Data Index: 194783 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.6432. Min Act: -0.1700
Data Index: 4588017 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.6119. Min Act: -0.1700
Data Index: 5047280 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.5807. Min Act: -0.1700
Data Index: 3706239 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.5182. Min Act: -0.1700
Data Index: 269514 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1744. Min Range: -7.1744
Max Act: 6.5182. Min Act: -0.1700
Data Index: 3970591 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19