Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4589 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.9653. Min Act: -0.1700
Data Index: 5795670 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.9028. Min Act: -0.1700
Data Index: 8647331 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.8403. Min Act: -0.1700
Data Index: 2320126 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.7465. Min Act: -0.1700
Data Index: 2267007 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.7465. Min Act: -0.1700
Data Index: 7727268 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.7153. Min Act: -0.1700
Data Index: 4970442 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6840. Min Act: -0.1700
Data Index: 7701901 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6840. Min Act: -0.1700
Data Index: 6889799 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6840. Min Act: -0.1700
Data Index: 2165797 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6840. Min Act: -0.1700
Data Index: 6871887 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6528. Min Act: -0.1700
Data Index: 1583903 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6528. Min Act: -0.1700
Data Index: 7894277 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.6215. Min Act: -0.1700
Data Index: 3169941 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5903. Min Act: -0.1700
Data Index: 2409273 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5903. Min Act: -0.1700
Data Index: 2957725 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5903. Min Act: -0.1700
Data Index: 1492633 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5590. Min Act: -0.1700
Data Index: 375174 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5903. Min Act: -0.1700
Data Index: 7574069 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5590. Min Act: -0.1700
Data Index: 350413 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9653. Min Range: -4.9653
Max Act: 4.5590. Min Act: -0.1700
Data Index: 7379648 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19