< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.7668. Min Act: -0.0000

Data Index: 145453 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.4944. Min Act: -0.0000

Data Index: 454690 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1852325 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.4517. Min Act: -0.0000

Data Index: 1453169 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.3712. Min Act: -0.0000

Data Index: 901666 (The Pile)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.4067. Min Act: -0.0000

Data Index: 688422 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.2611. Min Act: -0.0000

Data Index: 345154 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.3247. Min Act: -0.0000

Data Index: 760781 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1278694 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1908856 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.1947. Min Act: -0.0000

Data Index: 76350 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.2288. Min Act: -0.0000

Data Index: 738236 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.2154. Min Act: -0.0000

Data Index: 796887 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.1767. Min Act: -0.0000

Data Index: 80735 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.3558. Min Act: -0.0000

Data Index: 429885 (The Pile)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1984882 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1968956 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1519047 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.1724. Min Act: -0.0000

Data Index: 78866 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7668. Min Range: -1.7668

Max Act: 1.1513. Min Act: -0.0000

Data Index: 589203 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #19