Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.3903. Min Act: -0.1700
Data Index: 1683814 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.3903. Min Act: -0.1700
Data Index: 7486342 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.3590. Min Act: -0.1700
Data Index: 7318523 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.2965. Min Act: -0.1700
Data Index: 6090101 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.2028. Min Act: -0.1700
Data Index: 599037 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1715. Min Act: -0.1700
Data Index: 498654 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1715. Min Act: -0.1700
Data Index: 3042485 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1403. Min Act: -0.1700
Data Index: 8387080 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1403. Min Act: -0.1700
Data Index: 7579357 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1403. Min Act: -0.1700
Data Index: 6652779 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1090. Min Act: -0.1700
Data Index: 3106085 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1090. Min Act: -0.1700
Data Index: 1958079 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1090. Min Act: -0.1700
Data Index: 4535726 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1090. Min Act: -0.1700
Data Index: 7821718 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1090. Min Act: -0.1700
Data Index: 6684986 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.0778. Min Act: -0.1700
Data Index: 945813 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.1090. Min Act: -0.1700
Data Index: 7203431 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.0778. Min Act: -0.1700
Data Index: 24899 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.0778. Min Act: -0.1700
Data Index: 5675921 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3903. Min Range: -5.3903
Max Act: 5.0778. Min Act: -0.1700
Data Index: 5103584 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19