Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1830 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.5859. Min Act: -0.1700
Data Index: 7398579 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.5546. Min Act: -0.1700
Data Index: 1047523 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.4921. Min Act: -0.1700
Data Index: 1833252 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.4609. Min Act: -0.1700
Data Index: 6289171 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.4296. Min Act: -0.1700
Data Index: 464739 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.3046. Min Act: -0.1700
Data Index: 2512203 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.2734. Min Act: -0.1700
Data Index: 1739159 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.2734. Min Act: -0.1700
Data Index: 2755277 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.2421. Min Act: -0.1700
Data Index: 764879 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.2734. Min Act: -0.1700
Data Index: 3795729 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.2421. Min Act: -0.1700
Data Index: 6060801 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.2109. Min Act: -0.1700
Data Index: 8794130 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1796. Min Act: -0.1700
Data Index: 1353821 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1796. Min Act: -0.1700
Data Index: 464745 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4624608 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1796. Min Act: -0.1700
Data Index: 1182170 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1484. Min Act: -0.1700
Data Index: 7595954 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4449608 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1484. Min Act: -0.1700
Data Index: 6597330 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5859. Min Range: -5.5859
Max Act: 5.1484. Min Act: -0.1700
Data Index: 56625 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19