Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.5859. Min Act: -0.1700
Data Index: 7808869 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.3047. Min Act: -0.1700
Data Index: 1542007 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.3047. Min Act: -0.1700
Data Index: 7704932 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.2422. Min Act: -0.1700
Data Index: 791601 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.2109. Min Act: -0.1700
Data Index: 8375861 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.0859. Min Act: -0.1700
Data Index: 5180430 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.0234. Min Act: -0.1700
Data Index: 7027002 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5859. Min Range: -7.5859
Max Act: 7.0234. Min Act: -0.1700
Data Index: 7507599 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.9922. Min Act: -0.1700
Data Index: 6955430 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.9609. Min Act: -0.1700
Data Index: 6954891 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.9609. Min Act: -0.1700
Data Index: 2973485 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.9297. Min Act: -0.1700
Data Index: 1412899 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.9297. Min Act: -0.1700
Data Index: 1458871 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8984. Min Act: -0.1700
Data Index: 6809356 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8984. Min Act: -0.1700
Data Index: 8267554 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8984. Min Act: -0.1700
Data Index: 3655967 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8672. Min Act: -0.1700
Data Index: 7676815 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8672. Min Act: -0.1700
Data Index: 8336503 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8047. Min Act: -0.1700
Data Index: 278048 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5859. Min Range: -7.5859
Max Act: 6.8047. Min Act: -0.1700
Data Index: 2878671 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19