Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3925 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.9938. Min Act: -0.1699
Data Index: 7287473 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.5563. Min Act: -0.1700
Data Index: 6028162 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.2438. Min Act: -0.1700
Data Index: 7964778 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.1813. Min Act: -0.1700
Data Index: 933513 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.1188. Min Act: -0.1700
Data Index: 4168619 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.1813. Min Act: -0.1700
Data Index: 7309080 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.1813. Min Act: -0.1700
Data Index: 6028163 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.9938. Min Range: -13.9938
Max Act: 13.0563. Min Act: -0.1700
Data Index: 2099063 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.9938. Min Act: -0.1700
Data Index: 2896141 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.9313. Min Act: -0.1700
Data Index: 477961 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.9313. Min Act: -0.1700
Data Index: 3777338 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.8688. Min Act: -0.1700
Data Index: 6782191 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.8688. Min Act: -0.1700
Data Index: 3787138 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.8688. Min Act: -0.1700
Data Index: 7843819 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.8688. Min Act: -0.1700
Data Index: 4307838 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.8688. Min Act: -0.1700
Data Index: 5212939 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.7438. Min Act: -0.1700
Data Index: 5032321 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.6813. Min Act: -0.1700
Data Index: 2824105 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.6188. Min Act: -0.1700
Data Index: 7744152 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.9938. Min Range: -13.9938
Max Act: 12.6813. Min Act: -0.1700
Data Index: 6528801 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19