< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 16 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: 0.2254. Min Range: -0.2254

Max Act: 0.2254. Min Act: -0.0004

Data Index: 1673200 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1828. Min Act: -0.0004

Data Index: 154211 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1931. Min Act: -0.0004

Data Index: 667847 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1967. Min Act: -0.0004

Data Index: 1830836 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1757. Min Act: -0.0004

Data Index: 1327105 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1799. Min Act: -0.0004

Data Index: 1180242 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1726. Min Act: -0.0004

Data Index: 1002396 (The Pile)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1815. Min Act: -0.0004

Data Index: 1390434 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1646. Min Act: -0.0004

Data Index: 1439874 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1649. Min Act: -0.0004

Data Index: 398797 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1642. Min Act: -0.0004

Data Index: 565644 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1632. Min Act: -0.0004

Data Index: 882125 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1763. Min Act: -0.0004

Data Index: 1888067 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1688. Min Act: -0.0004

Data Index: 642446 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1691. Min Act: -0.0004

Data Index: 53690 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1748. Min Act: -0.0004

Data Index: 776157 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1708. Min Act: -0.0004

Data Index: 1234341 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1637. Min Act: -0.0004

Data Index: 1955289 (The Pile)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1762. Min Act: -0.0004

Data Index: 1475134 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2254. Min Range: -0.2254

Max Act: 0.1626. Min Act: -0.0005

Data Index: 1381791 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #19