< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 20 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1741530 (The Pile)

Max Activating Token Index: 90

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3334. Min Act: -0.0000

Data Index: 160018 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1661724 (The Pile)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1857461 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3311. Min Act: -0.0000

Data Index: 234931 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3329. Min Act: -0.0000

Data Index: 369963 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3275. Min Act: -0.0000

Data Index: 916042 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1912094 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1638429 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1269534 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1106321 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1578669 (The Pile)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1057812 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1690817 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1918188 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2915. Min Act: -0.0000

Data Index: 957701 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3150. Min Act: -0.0000

Data Index: 677038 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1606274 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1831511 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3702. Min Range: -0.3702

Max Act: 0.2865. Min Act: -0.0000

Data Index: 810427 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #19