< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 23 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2783. Min Range: -3.2783

Max Act: 3.2783. Min Act: -0.0000

Data Index: 1508433 (The Pile)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3879. Min Act: -0.0000

Data Index: 1111033 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.6121. Min Act: -0.0000

Data Index: 929303 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.4187. Min Act: -0.0000

Data Index: 1546425 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.5238. Min Act: -0.0000

Data Index: 1031776 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.5147. Min Act: -0.0000

Data Index: 565027 (The Pile)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3931. Min Act: -0.0000

Data Index: 416927 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.6241. Min Act: -0.0000

Data Index: 341664 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3654. Min Act: -0.0000

Data Index: 73388 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.6172. Min Act: -0.0000

Data Index: 590308 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.4924. Min Act: -0.0000

Data Index: 1239000 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.6184. Min Act: -0.0000

Data Index: 460070 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1425767 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3678. Min Act: -0.0000

Data Index: 1229481 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3502. Min Act: -0.0000

Data Index: 431669 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.4555. Min Act: -0.0000

Data Index: 405410 (The Pile)

Max Activating Token Index: 293

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3236. Min Act: -0.0000

Data Index: 529201 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.8413. Min Act: -0.0000

Data Index: 303139 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.5615. Min Act: -0.0000

Data Index: 1453846 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2783. Min Range: -3.2783

Max Act: 2.3037. Min Act: -0.0000

Data Index: 1986360 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #19