< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2015 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 4329 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 42880 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1699

Data Index: 40794 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 40449 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 40078 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 5371 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 39045 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1699

Data Index: 37995 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 37346 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1699

Data Index: 36782 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 7045 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 35643 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 4173 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1699

Data Index: 34330 (The Pile)

Max Activating Token Index: 585

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 20310 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 13328 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 11025 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 8523 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 7971 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7301. Min Range: -1.7301

Max Act: 1.7301. Min Act: -0.1700

Data Index: 7874 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #19