Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.7779. Min Act: -0.1700
Data Index: 7566780 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.7154. Min Act: -0.1700
Data Index: 1210021 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.6997. Min Act: -0.1700
Data Index: 7566778 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.6841. Min Act: -0.1700
Data Index: 7566776 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.6841. Min Act: -0.1700
Data Index: 4645393 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.6684. Min Act: -0.1700
Data Index: 3870753 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5902. Min Act: -0.1700
Data Index: 7569102 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5745. Min Act: -0.1700
Data Index: 1205971 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5902. Min Act: -0.1700
Data Index: 1915509 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5589. Min Act: -0.1700
Data Index: 7566777 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5589. Min Act: -0.1700
Data Index: 1261588 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5432. Min Act: -0.1700
Data Index: 3502955 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.5119. Min Act: -0.1700
Data Index: 1700368 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4806. Min Act: -0.1700
Data Index: 954665 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4806. Min Act: -0.1700
Data Index: 8425570 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4492. Min Act: -0.1700
Data Index: 277925 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4492. Min Act: -0.1700
Data Index: 1040830 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4806. Min Act: -0.1700
Data Index: 1284558 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4806. Min Act: -0.1700
Data Index: 5134902 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7779. Min Range: -3.7779
Max Act: 3.4492. Min Act: -0.1700
Data Index: 8368503 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19