Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1085 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0616. Min Range: -8.0616
Max Act: 8.0616. Min Act: -0.1700
Data Index: 3968632 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.8741. Min Act: -0.1700
Data Index: 4512991 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.7491. Min Act: -0.1700
Data Index: 2201930 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6866. Min Act: -0.1700
Data Index: 347477 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 646644 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.7491. Min Act: -0.1700
Data Index: 222342 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 6357305 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.6241. Min Act: -0.1700
Data Index: 5393232 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.5616. Min Act: -0.1700
Data Index: 6460078 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.5616. Min Act: -0.1700
Data Index: 5656491 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.4991. Min Act: -0.1700
Data Index: 7926221 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.4991. Min Act: -0.1700
Data Index: 2759623 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.4366. Min Act: -0.1700
Data Index: 529679 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.4366. Min Act: -0.1700
Data Index: 6783050 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.4054. Min Act: -0.1700
Data Index: 3550306 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.4366. Min Act: -0.1700
Data Index: 8688447 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.3741. Min Act: -0.1700
Data Index: 7088031 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.3429. Min Act: -0.1700
Data Index: 953955 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.3429. Min Act: -0.1700
Data Index: 4884724 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0616. Min Range: -8.0616
Max Act: 7.3429. Min Act: -0.1700
Data Index: 4554387 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19