< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 17 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: 1.7194. Min Range: -1.7194

Max Act: 1.7194. Min Act: -0.0001

Data Index: 683439 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.4197. Min Act: -0.0000

Data Index: 534468 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.2628. Min Act: -0.0001

Data Index: 89532 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.4367. Min Act: -0.0001

Data Index: 1175433 (The Pile)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.3404. Min Act: -0.0000

Data Index: 488830 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1269513 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1338232 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.2188. Min Act: -0.0001

Data Index: 1837968 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1526278 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.1157. Min Act: -0.0001

Data Index: 577373 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.2319. Min Act: -0.0000

Data Index: 78633 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.1602. Min Act: -0.0000

Data Index: 875177 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.2646. Min Act: -0.0001

Data Index: 1887509 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.0698. Min Act: -0.0001

Data Index: 728506 (The Pile)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.0592. Min Act: -0.0001

Data Index: 1848079 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.2487. Min Act: -0.0000

Data Index: 446049 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.0101. Min Act: -0.0000

Data Index: 680975 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.0836. Min Act: -0.0001

Data Index: 1167851 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.1097. Min Act: -0.0000

Data Index: 495698 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7194. Min Range: -1.7194

Max Act: 1.0752. Min Act: -0.0001

Data Index: 1553943 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #19