Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1626. Min Act: -0.1700
Data Index: 647650 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1626. Min Act: -0.1700
Data Index: 4058896 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.9438. Min Act: -0.1700
Data Index: 3112565 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.9750. Min Act: -0.1700
Data Index: 3803761 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.9750. Min Act: -0.1700
Data Index: 4798985 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.9438. Min Act: -0.1700
Data Index: 3256521 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 3403471 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.9125. Min Act: -0.1700
Data Index: 6011792 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.9125. Min Act: -0.1700
Data Index: 3112551 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 8689637 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 3403463 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 4204415 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 1027478 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 2712444 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8500. Min Act: -0.1700
Data Index: 8357928 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8500. Min Act: -0.1700
Data Index: 8203363 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8500. Min Act: -0.1700
Data Index: 8098687 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8500. Min Act: -0.1700
Data Index: 4062576 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8500. Min Act: -0.1700
Data Index: 4875892 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1626. Min Range: -4.1626
Max Act: 3.8812. Min Act: -0.1700
Data Index: 7609745 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19