Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4466 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.8734. Min Act: -0.1700
Data Index: 4607526 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.6859. Min Act: -0.1700
Data Index: 2042619 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.5609. Min Act: -0.1700
Data Index: 7805686 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.4671. Min Act: -0.1700
Data Index: 4109447 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.4359. Min Act: -0.1700
Data Index: 5627542 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3734. Min Act: -0.1700
Data Index: 3560085 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.4046. Min Act: -0.1700
Data Index: 7930220 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3734. Min Act: -0.1700
Data Index: 6391973 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3421. Min Act: -0.1700
Data Index: 3032079 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3734. Min Act: -0.1700
Data Index: 6341559 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3734. Min Act: -0.1700
Data Index: 1408104 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3734. Min Act: -0.1700
Data Index: 436325 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3109. Min Act: -0.1700
Data Index: 2662402 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3421. Min Act: -0.1700
Data Index: 8210289 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3109. Min Act: -0.1700
Data Index: 3838326 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.3109. Min Act: -0.1700
Data Index: 3226635 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.2796. Min Act: -0.1700
Data Index: 183975 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.2484. Min Act: -0.1700
Data Index: 218665 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.2484. Min Act: -0.1700
Data Index: 7739814 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8734. Min Range: -6.8734
Max Act: 6.2171. Min Act: -0.1700
Data Index: 6391155 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19