Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3876 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.2040. Min Act: -0.1700
Data Index: 8742226 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.2040. Min Act: -0.1700
Data Index: 3242607 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.1415. Min Act: -0.1700
Data Index: 6516967 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.1415. Min Act: -0.1700
Data Index: 3221212 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.1415. Min Act: -0.1700
Data Index: 5246182 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.0165. Min Act: -0.1700
Data Index: 4934825 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.0165. Min Act: -0.1700
Data Index: 2436922 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2040. Min Range: -8.2040
Max Act: 8.0165. Min Act: -0.1700
Data Index: 931379 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.9540. Min Act: -0.1700
Data Index: 3158895 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.9540. Min Act: -0.1700
Data Index: 5725385 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.9540. Min Act: -0.1700
Data Index: 840913 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.9540. Min Act: -0.1700
Data Index: 2236146 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.9540. Min Act: -0.1700
Data Index: 3679505 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.8915. Min Act: -0.1700
Data Index: 8725061 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.8915. Min Act: -0.1700
Data Index: 7267345 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.8915. Min Act: -0.1700
Data Index: 1531863 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.8915. Min Act: -0.1700
Data Index: 44469 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.8915. Min Act: -0.1700
Data Index: 7613267 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.7977. Min Act: -0.1700
Data Index: 6656775 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2040. Min Range: -8.2040
Max Act: 7.7665. Min Act: -0.1700
Data Index: 8397118 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19