Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.4377. Min Act: -0.1700
Data Index: 5223345 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.4377. Min Act: -0.1700
Data Index: 5122852 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.4690. Min Act: -0.1700
Data Index: 7335000 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.3752. Min Act: -0.1700
Data Index: 2542815 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.3752. Min Act: -0.1700
Data Index: 3076418 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.2815. Min Act: -0.1700
Data Index: 209057 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.3127. Min Act: -0.1700
Data Index: 1096502 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.2190. Min Act: -0.1700
Data Index: 1636072 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1877. Min Act: -0.1700
Data Index: 1938391 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1877. Min Act: -0.1700
Data Index: 7537636 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1877. Min Act: -0.1700
Data Index: 2342015 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1565. Min Act: -0.1700
Data Index: 7181675 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1565. Min Act: -0.1700
Data Index: 6314912 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1565. Min Act: -0.1700
Data Index: 6122832 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1565. Min Act: -0.1700
Data Index: 7568789 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.0940. Min Act: -0.1700
Data Index: 4813108 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.0940. Min Act: -0.1700
Data Index: 454221 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1252. Min Act: -0.1700
Data Index: 5375630 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.1252. Min Act: -0.1700
Data Index: 4260001 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4690. Min Range: -7.4690
Max Act: 7.0940. Min Act: -0.1700
Data Index: 4559486 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19