Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5412 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.2285. Min Act: -0.1700
Data Index: 8743057 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.2285. Min Act: -0.1700
Data Index: 2852844 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.1347. Min Act: -0.1700
Data Index: 8817332 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.1347. Min Act: -0.1700
Data Index: 6527289 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.1035. Min Act: -0.1700
Data Index: 3277204 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 4953570 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 1680842 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0410. Min Act: -0.1700
Data Index: 5153735 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0097. Min Act: -0.1700
Data Index: 1882597 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0097. Min Act: -0.1700
Data Index: 7371183 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0097. Min Act: -0.1700
Data Index: 6924922 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2285. Min Range: -5.2285
Max Act: 5.0097. Min Act: -0.1700
Data Index: 3948889 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 4882985 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 1797690 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 4898408 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 95336 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9472. Min Act: -0.1700
Data Index: 3197924 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 6625621 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9785. Min Act: -0.1700
Data Index: 354810 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2285. Min Range: -5.2285
Max Act: 4.9472. Min Act: -0.1700
Data Index: 6325270 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19