< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 17 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: 2.6477. Min Range: -2.6477

Max Act: 2.6477. Min Act: -0.1700

Data Index: 1885647 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5672. Min Act: -0.1700

Data Index: 1606019 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5511. Min Act: -0.1700

Data Index: 1016158 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5511. Min Act: -0.1700

Data Index: 5706193 (The Pile)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5511. Min Act: -0.1700

Data Index: 3190919 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5350. Min Act: -0.1700

Data Index: 2759476 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5188. Min Act: -0.1700

Data Index: 6812129 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5188. Min Act: -0.1700

Data Index: 5976128 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.5026. Min Act: -0.1700

Data Index: 4500288 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4702. Min Act: -0.1700

Data Index: 10783439 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4377. Min Act: -0.1700

Data Index: 8575699 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4377. Min Act: -0.1700

Data Index: 6726563 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4377. Min Act: -0.1700

Data Index: 114739 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4377. Min Act: -0.1700

Data Index: 977921 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4377. Min Act: -0.1700

Data Index: 6311537 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4377. Min Act: -0.1700

Data Index: 9150622 (The Pile)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4214. Min Act: -0.1700

Data Index: 1255521 (The Pile)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4214. Min Act: -0.1700

Data Index: 3318584 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4214. Min Act: -0.1700

Data Index: 6352430 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6477. Min Range: -2.6477

Max Act: 2.4214. Min Act: -0.1700

Data Index: 2861842 (The Pile)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #19