Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5786 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.9829. Min Act: -0.1700
Data Index: 5083589 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.7016. Min Act: -0.1700
Data Index: 1243192 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.6391. Min Act: -0.1700
Data Index: 1671649 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.6391. Min Act: -0.1700
Data Index: 2435422 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.6079. Min Act: -0.1700
Data Index: 6113293 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.6079. Min Act: -0.1700
Data Index: 8526966 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.6079. Min Act: -0.1700
Data Index: 7100368 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.5766. Min Act: -0.1700
Data Index: 2088403 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.5766. Min Act: -0.1700
Data Index: 4183290 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.5454. Min Act: -0.1700
Data Index: 873614 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.5141. Min Act: -0.1700
Data Index: 5572614 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.5454. Min Act: -0.1700
Data Index: 8729933 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4829. Min Act: -0.1700
Data Index: 7147954 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4829. Min Act: -0.1700
Data Index: 752638 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.5141. Min Act: -0.1700
Data Index: 4214440 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4516. Min Act: -0.1700
Data Index: 3958771 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4516. Min Act: -0.1700
Data Index: 748112 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4516. Min Act: -0.1700
Data Index: 4883614 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4204. Min Act: -0.1700
Data Index: 970801 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9829. Min Range: -4.9829
Max Act: 4.4204. Min Act: -0.1700
Data Index: 3638055 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19