Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1780. Min Range: -5.1780
Max Act: 5.1780. Min Act: -0.1700
Data Index: 8700812 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1780. Min Range: -5.1780
Max Act: 5.1468. Min Act: -0.1700
Data Index: 4266738 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1780. Min Range: -5.1780
Max Act: 5.0843. Min Act: -0.1700
Data Index: 5522141 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1780. Min Range: -5.1780
Max Act: 5.0218. Min Act: -0.1700
Data Index: 8266919 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1780. Min Range: -5.1780
Max Act: 5.0218. Min Act: -0.1700
Data Index: 821958 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.9593. Min Act: -0.1700
Data Index: 2996784 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.9593. Min Act: -0.1700
Data Index: 2151085 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.9280. Min Act: -0.1700
Data Index: 8797580 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.9280. Min Act: -0.1700
Data Index: 6585847 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8655. Min Act: -0.1700
Data Index: 5824426 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8655. Min Act: -0.1700
Data Index: 3541589 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8343. Min Act: -0.1700
Data Index: 4872859 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8030. Min Act: -0.1700
Data Index: 357552 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8343. Min Act: -0.1700
Data Index: 7501814 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8343. Min Act: -0.1700
Data Index: 4814713 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8343. Min Act: -0.1700
Data Index: 1119043 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8343. Min Act: -0.1700
Data Index: 4331425 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8343. Min Act: -0.1700
Data Index: 2277918 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8030. Min Act: -0.1700
Data Index: 3789667 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1780. Min Range: -5.1780
Max Act: 4.8030. Min Act: -0.1700
Data Index: 4363742 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19