Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0859. Min Range: -7.0859
Max Act: 7.0859. Min Act: -0.1700
Data Index: 6438649 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.9609. Min Act: -0.1700
Data Index: 1987699 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.9609. Min Act: -0.1700
Data Index: 7256319 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.9297. Min Act: -0.1700
Data Index: 420284 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8672. Min Act: -0.1700
Data Index: 8491545 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8672. Min Act: -0.1700
Data Index: 6678391 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8672. Min Act: -0.1700
Data Index: 6702918 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8672. Min Act: -0.1700
Data Index: 7685160 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8047. Min Act: -0.1700
Data Index: 7224297 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8047. Min Act: -0.1700
Data Index: 2008285 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.8047. Min Act: -0.1700
Data Index: 4611068 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.7734. Min Act: -0.1700
Data Index: 5270661 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.7422. Min Act: -0.1700
Data Index: 3507174 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.7422. Min Act: -0.1700
Data Index: 3681737 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.7422. Min Act: -0.1700
Data Index: 5560969 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.7109. Min Act: -0.1700
Data Index: 1088716 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.7109. Min Act: -0.1700
Data Index: 3904773 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.6797. Min Act: -0.1700
Data Index: 1731255 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.6797. Min Act: -0.1700
Data Index: 1988475 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0859. Min Range: -7.0859
Max Act: 6.6797. Min Act: -0.1700
Data Index: 7227997 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19