< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.2122. Min Act: -0.0001

Data Index: 432705 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.2223. Min Act: -0.0001

Data Index: 1072662 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.2290. Min Act: -0.0001

Data Index: 1519709 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.1630. Min Act: -0.0001

Data Index: 519477 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.1854. Min Act: -0.0001

Data Index: 577370 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.0875. Min Act: -0.0001

Data Index: 1563975 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.1122. Min Act: -0.0001

Data Index: 1235037 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.0180. Min Act: -0.0001

Data Index: 1625750 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.9541. Min Act: -0.0001

Data Index: 447382 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.0962. Min Act: -0.0001

Data Index: 1244000 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.0289. Min Act: -0.0001

Data Index: 1755431 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.0279. Min Act: -0.0001

Data Index: 1055580 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.1056. Min Act: -0.0001

Data Index: 954940 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.9911. Min Act: -0.0001

Data Index: 950349 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.9752. Min Act: -0.0001

Data Index: 544414 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.9788. Min Act: -0.0001

Data Index: 186978 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2290. Min Range: -2.2290

Max Act: 2.0155. Min Act: -0.0001

Data Index: 417816 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.9528. Min Act: -0.0001

Data Index: 1735742 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.8994. Min Act: -0.0001

Data Index: 799816 (The Pile)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2290. Min Range: -2.2290

Max Act: 1.8748. Min Act: -0.0001

Data Index: 766107 (The Pile)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #19