< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 57 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: 0.0656. Min Range: -0.0656

Max Act: 0.0641. Min Act: -0.0004

Data Index: 1034218 (The Pile)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0656. Min Act: -0.0004

Data Index: 139173 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0646. Min Act: -0.0004

Data Index: 1896373 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0620. Min Act: -0.0004

Data Index: 1897793 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0589. Min Act: -0.0004

Data Index: 650709 (The Pile)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0559. Min Act: -0.0004

Data Index: 1370069 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0588. Min Act: -0.0004

Data Index: 1347331 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0570. Min Act: -0.0004

Data Index: 340725 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0570. Min Act: -0.0004

Data Index: 397237 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0530. Min Act: -0.0004

Data Index: 98878 (The Pile)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0586. Min Act: -0.0004

Data Index: 1905855 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0553. Min Act: -0.0004

Data Index: 681207 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0584. Min Act: -0.0004

Data Index: 1008470 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0546. Min Act: -0.0004

Data Index: 620060 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0555. Min Act: -0.0004

Data Index: 1509544 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0544. Min Act: -0.0004

Data Index: 365708 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0555. Min Act: -0.0004

Data Index: 187978 (The Pile)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0562. Min Act: -0.0004

Data Index: 459955 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0549. Min Act: -0.0004

Data Index: 1785923 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0656. Min Range: -0.0656

Max Act: 0.0547. Min Act: -0.0004

Data Index: 547107 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #19