Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5015 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9469. Min Act: -0.1700
Data Index: 780122 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9782. Min Act: -0.1700
Data Index: 2893700 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9782. Min Act: -0.1700
Data Index: 4310880 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9782. Min Act: -0.1700
Data Index: 8079168 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.9782. Min Act: -0.1700
Data Index: 2210381 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.8844. Min Act: -0.1700
Data Index: 6248718 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.8219. Min Act: -0.1700
Data Index: 3559539 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.8532. Min Act: -0.1700
Data Index: 7566939 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6969. Min Act: -0.1700
Data Index: 5165884 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6657. Min Act: -0.1700
Data Index: 6185535 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6657. Min Act: -0.1700
Data Index: 7188351 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6657. Min Act: -0.1700
Data Index: 6022477 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6344. Min Act: -0.1700
Data Index: 7915 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6032. Min Act: -0.1700
Data Index: 7975633 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6032. Min Act: -0.1700
Data Index: 2476198 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6344. Min Act: -0.1700
Data Index: 3161261 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6032. Min Act: -0.1700
Data Index: 1632847 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.6032. Min Act: -0.1700
Data Index: 1778716 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 2033704 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9782. Min Range: -5.9782
Max Act: 5.5719. Min Act: -0.1700
Data Index: 4524583 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19