< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 37 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.8159. Min Act: -0.1700

Data Index: 6841975 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.8159. Min Act: -0.1700

Data Index: 6477975 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.8159. Min Act: -0.1700

Data Index: 5765563 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.7534. Min Act: -0.1700

Data Index: 1490734 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.7221. Min Act: -0.1700

Data Index: 2132222 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.7221. Min Act: -0.1700

Data Index: 6785809 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.7221. Min Act: -0.1700

Data Index: 7745778 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.7221. Min Act: -0.1700

Data Index: 2036127 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6909. Min Act: -0.1699

Data Index: 2263006 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6909. Min Act: -0.1700

Data Index: 3632936 (The Pile)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6596. Min Act: -0.1700

Data Index: 6089705 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6596. Min Act: -0.1700

Data Index: 4528179 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6284. Min Act: -0.1700

Data Index: 6237174 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6284. Min Act: -0.1700

Data Index: 9209210 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6284. Min Act: -0.1700

Data Index: 4492720 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.6284. Min Act: -0.1700

Data Index: 7761115 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.5971. Min Act: -0.1700

Data Index: 7295017 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.5971. Min Act: -0.1700

Data Index: 9689631 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.5971. Min Act: -0.1700

Data Index: 8099205 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8159. Min Range: -4.8159

Max Act: 4.5659. Min Act: -0.1700

Data Index: 2410048 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #19