< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1475. Min Act: -0.0004

Data Index: 112533 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1454. Min Act: -0.0004

Data Index: 887354 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1490. Min Act: -0.0004

Data Index: 1027477 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1364. Min Act: -0.0004

Data Index: 1815240 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1417. Min Act: -0.0004

Data Index: 1415023 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1381. Min Act: -0.0004

Data Index: 1785079 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1378. Min Act: -0.0004

Data Index: 1920452 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1315. Min Act: -0.0004

Data Index: 807876 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1363. Min Act: -0.0004

Data Index: 1455303 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1341. Min Act: -0.0004

Data Index: 1426683 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1292. Min Act: -0.0004

Data Index: 1660287 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1334. Min Act: -0.0004

Data Index: 861496 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1333. Min Act: -0.0004

Data Index: 1235829 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1330. Min Act: -0.0004

Data Index: 494716 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1330. Min Act: -0.0004

Data Index: 774588 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1326. Min Act: -0.0004

Data Index: 1569529 (The Pile)

Max Activating Token Index: 783

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1347. Min Act: -0.0004

Data Index: 1281957 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1342. Min Act: -0.0004

Data Index: 1638209 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1320. Min Act: -0.0004

Data Index: 1721668 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1313. Min Act: -0.0004

Data Index: 582772 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #19