Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.8554. Min Act: -0.1685
Data Index: 2329621 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.8048. Min Act: -0.1691
Data Index: 8768808 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6890. Min Act: -0.1589
Data Index: 8494637 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6567. Min Act: -0.1589
Data Index: 1011447 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6567. Min Act: -0.1696
Data Index: 2356098 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6407. Min Act: -0.1698
Data Index: 2285413 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6407. Min Act: -0.1700
Data Index: 2101733 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6089. Min Act: -0.1635
Data Index: 8768807 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6089. Min Act: -0.1700
Data Index: 2285415 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6089. Min Act: -0.1699
Data Index: 7657201 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6089. Min Act: -0.1700
Data Index: 2285408 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6010. Min Act: -0.1589
Data Index: 5620795 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.6010. Min Act: -0.1700
Data Index: 2285411 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5697. Min Act: -0.1637
Data Index: 5600375 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5775. Min Act: -0.1672
Data Index: 2327608 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5697. Min Act: -0.1693
Data Index: 1851621 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5853. Min Act: -0.1698
Data Index: 7657197 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5697. Min Act: -0.1700
Data Index: 2285404 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5542. Min Act: -0.1589
Data Index: 1648616 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8554. Min Range: -0.8554
Max Act: 0.5542. Min Act: -0.1691
Data Index: 4403433 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19