< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 25 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.6594. Min Act: -0.0001

Data Index: 1480065 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.5171. Min Act: -0.0001

Data Index: 1922054 (The Pile)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.5490. Min Act: -0.0001

Data Index: 156177 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.4425. Min Act: -0.0001

Data Index: 398899 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.3924. Min Act: -0.0001

Data Index: 678961 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.4573. Min Act: -0.0000

Data Index: 186862 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.3401. Min Act: -0.0001

Data Index: 1592318 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2615. Min Act: -0.0001

Data Index: 1092864 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.4388. Min Act: -0.0001

Data Index: 871437 (The Pile)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.3895. Min Act: -0.0001

Data Index: 352478 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2001. Min Act: -0.0001

Data Index: 1981383 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2874. Min Act: -0.0001

Data Index: 127989 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2617. Min Act: -0.0001

Data Index: 1399276 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2563. Min Act: -0.0001

Data Index: 24083 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2680. Min Act: -0.0001

Data Index: 301433 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2732. Min Act: -0.0001

Data Index: 769742 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2234. Min Act: -0.0001

Data Index: 1999151 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2350. Min Act: -0.0001

Data Index: 1873035 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2450. Min Act: -0.0001

Data Index: 1943529 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6594. Min Range: -1.6594

Max Act: 1.2629. Min Act: -0.0001

Data Index: 1462149 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #19