Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5891 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.1830. Min Act: -0.1700
Data Index: 908636 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.1830. Min Act: -0.1700
Data Index: 2887323 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.1517. Min Act: -0.1700
Data Index: 7299127 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.0580. Min Act: -0.1700
Data Index: 4028463 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.0580. Min Act: -0.1700
Data Index: 3080472 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.0580. Min Act: -0.1700
Data Index: 8036665 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1830. Min Range: -5.1830
Max Act: 5.0267. Min Act: -0.1700
Data Index: 5355299 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9955. Min Act: -0.1700
Data Index: 8724667 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9642. Min Act: -0.1700
Data Index: 4837311 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9642. Min Act: -0.1700
Data Index: 6187508 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9642. Min Act: -0.1700
Data Index: 1853701 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6505742 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9330. Min Act: -0.1700
Data Index: 6151833 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9330. Min Act: -0.1700
Data Index: 5041779 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9330. Min Act: -0.1700
Data Index: 7782887 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.8705. Min Act: -0.1700
Data Index: 5782107 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9017. Min Act: -0.1700
Data Index: 4179141 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.9017. Min Act: -0.1700
Data Index: 2128328 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.8705. Min Act: -0.1700
Data Index: 6151832 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1830. Min Range: -5.1830
Max Act: 4.8705. Min Act: -0.1700
Data Index: 4324612 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19