Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1489 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.9585. Min Act: -0.1700
Data Index: 8211024 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.8960. Min Act: -0.1700
Data Index: 8657190 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.8648. Min Act: -0.1700
Data Index: 3550081 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.8648. Min Act: -0.1700
Data Index: 5601880 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.8335. Min Act: -0.1700
Data Index: 5693829 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.8335. Min Act: -0.1700
Data Index: 8200285 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.7398. Min Act: -0.1700
Data Index: 20311 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.7085. Min Act: -0.1700
Data Index: 545335 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.6460. Min Act: -0.1700
Data Index: 5291699 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.6460. Min Act: -0.1700
Data Index: 1530057 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5835. Min Act: -0.1700
Data Index: 7671392 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5523. Min Act: -0.1700
Data Index: 6574858 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5523. Min Act: -0.1700
Data Index: 1655626 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.4898. Min Act: -0.1700
Data Index: 3999806 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5210. Min Act: -0.1700
Data Index: 6835445 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5210. Min Act: -0.1700
Data Index: 6638259 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5210. Min Act: -0.1700
Data Index: 825378 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5210. Min Act: -0.1700
Data Index: 3864480 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5210. Min Act: -0.1700
Data Index: 3999810 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9585. Min Range: -5.9585
Max Act: 5.5210. Min Act: -0.1700
Data Index: 2637749 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19