< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 14 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.4155. Min Act: -0.1700

Data Index: 680867 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3843. Min Act: -0.1700

Data Index: 1729366 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3843. Min Act: -0.1700

Data Index: 7192389 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3843. Min Act: -0.1700

Data Index: 10255227 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3843. Min Act: -0.1700

Data Index: 743856 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3843. Min Act: -0.1700

Data Index: 4970687 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3530. Min Act: -0.1700

Data Index: 1639083 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3530. Min Act: -0.1700

Data Index: 3406912 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3218. Min Act: -0.1700

Data Index: 8593031 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3218. Min Act: -0.1700

Data Index: 68231 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.3218. Min Act: -0.1700

Data Index: 5893670 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2905. Min Act: -0.1700

Data Index: 5634212 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2905. Min Act: -0.1700

Data Index: 5258983 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2905. Min Act: -0.1700

Data Index: 9523974 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2905. Min Act: -0.1700

Data Index: 8440004 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2905. Min Act: -0.1700

Data Index: 7136984 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2593. Min Act: -0.1700

Data Index: 5708485 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2593. Min Act: -0.1700

Data Index: 1967781 (The Pile)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2593. Min Act: -0.1700

Data Index: 6564962 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.4155. Min Range: -4.4155

Max Act: 4.2593. Min Act: -0.1700

Data Index: 6625335 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #19