< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 12 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.7805. Min Act: -0.0000

Data Index: 1181558 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.8984. Min Act: -0.0000

Data Index: 659300 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.6402. Min Act: -0.0000

Data Index: 1689653 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.5712. Min Act: -0.0000

Data Index: 540260 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.7152. Min Act: -0.0000

Data Index: 1078069 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.6360. Min Act: -0.0000

Data Index: 1350921 (The Pile)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.4779. Min Act: -0.0000

Data Index: 1028865 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.2676. Min Act: -0.0000

Data Index: 1693313 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.5931. Min Act: -0.0000

Data Index: 228229 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.5843. Min Act: -0.0000

Data Index: 766314 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.7146. Min Act: -0.0000

Data Index: 896632 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.5266. Min Act: -0.0000

Data Index: 153918 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.4976. Min Act: -0.0000

Data Index: 598156 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.3459. Min Act: -0.0000

Data Index: 284697 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.1533. Min Act: -0.0000

Data Index: 1071617 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.1747. Min Act: -0.0000

Data Index: 1725344 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.4857. Min Act: -0.0000

Data Index: 1683261 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.6084. Min Act: -0.0000

Data Index: 1605326 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.6100. Min Act: -0.0000

Data Index: 1253402 (The Pile)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8984. Min Range: -4.8984

Max Act: 4.5292. Min Act: -0.0000

Data Index: 1026669 (The Pile)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #19