< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4050 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0212. Min Range: -3.0212

Max Act: 3.0212. Min Act: -0.1700

Data Index: 2228511 (The Pile)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.9896. Min Act: -0.1700

Data Index: 7037454 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.9738. Min Act: -0.1700

Data Index: 4196846 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.9738. Min Act: -0.1700

Data Index: 10230996 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.9580. Min Act: -0.1700

Data Index: 6198609 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.9263. Min Act: -0.1700

Data Index: 9125272 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.9104. Min Act: -0.1700

Data Index: 7436743 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8628. Min Act: -0.1700

Data Index: 8964852 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8628. Min Act: -0.1700

Data Index: 7641072 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8469. Min Act: -0.1700

Data Index: 590019 (The Pile)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8469. Min Act: -0.1700

Data Index: 6359971 (The Pile)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8310. Min Act: -0.1700

Data Index: 1521759 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8151. Min Act: -0.1700

Data Index: 10521678 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.8151. Min Act: -0.1700

Data Index: 10477974 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.7992. Min Act: -0.1700

Data Index: 696618 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.7992. Min Act: -0.1700

Data Index: 6655687 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.7992. Min Act: -0.1700

Data Index: 6878803 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.7992. Min Act: -0.1700

Data Index: 9238852 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.7833. Min Act: -0.1700

Data Index: 8079627 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0212. Min Range: -3.0212

Max Act: 2.7833. Min Act: -0.1700

Data Index: 10650843 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #19