Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3259 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1704. Min Range: -7.1704
Max Act: 7.1704. Min Act: -0.1700
Data Index: 1769009 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1704. Min Range: -7.1704
Max Act: 7.1391. Min Act: -0.1700
Data Index: 6026200 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1704. Min Range: -7.1704
Max Act: 7.1391. Min Act: -0.1700
Data Index: 8245017 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1704. Min Range: -7.1704
Max Act: 7.0766. Min Act: -0.1700
Data Index: 4521782 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.9516. Min Act: -0.1700
Data Index: 340764 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.8891. Min Act: -0.1700
Data Index: 6332179 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.8579. Min Act: -0.1700
Data Index: 7039585 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.8266. Min Act: -0.1700
Data Index: 1793932 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.8266. Min Act: -0.1700
Data Index: 4260260 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.7641. Min Act: -0.1700
Data Index: 3557151 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.7329. Min Act: -0.1700
Data Index: 3990775 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.7329. Min Act: -0.1700
Data Index: 1431308 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.7329. Min Act: -0.1700
Data Index: 3091918 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.6704. Min Act: -0.1700
Data Index: 4973469 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.7016. Min Act: -0.1700
Data Index: 3145929 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.6079. Min Act: -0.1700
Data Index: 83624 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.6391. Min Act: -0.1700
Data Index: 5337162 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.6079. Min Act: -0.1700
Data Index: 3858265 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.6079. Min Act: -0.1700
Data Index: 6519211 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1704. Min Range: -7.1704
Max Act: 6.6391. Min Act: -0.1700
Data Index: 8119163 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19