< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 12 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.5271. Min Act: -0.1700

Data Index: 9303058 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4947. Min Act: -0.1700

Data Index: 891016 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4947. Min Act: -0.1700

Data Index: 10427834 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4947. Min Act: -0.1700

Data Index: 8461679 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4947. Min Act: -0.1700

Data Index: 10348181 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4785. Min Act: -0.1700

Data Index: 3647013 (The Pile)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4785. Min Act: -0.1700

Data Index: 4013745 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4785. Min Act: -0.1700

Data Index: 10066768 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4623. Min Act: -0.1700

Data Index: 402583 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4623. Min Act: -0.1700

Data Index: 4815106 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4623. Min Act: -0.1700

Data Index: 9667853 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4623. Min Act: -0.1700

Data Index: 7302620 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4623. Min Act: -0.1700

Data Index: 6918642 (The Pile)

Max Activating Token Index: 797

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4623. Min Act: -0.1700

Data Index: 6673064 (The Pile)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4461. Min Act: -0.1700

Data Index: 8263422 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4461. Min Act: -0.1699

Data Index: 9692625 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4461. Min Act: -0.1700

Data Index: 7831275 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4461. Min Act: -0.1700

Data Index: 4407553 (The Pile)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4461. Min Act: -0.1700

Data Index: 2062691 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5271. Min Range: -2.5271

Max Act: 2.4461. Min Act: -0.1700

Data Index: 5437498 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #19