< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 31 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: 2.1599. Min Range: -2.1599

Max Act: 2.1599. Min Act: -0.0001

Data Index: 1438268 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.9929. Min Act: -0.0001

Data Index: 42430 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.9738. Min Act: -0.0001

Data Index: 273982 (The Pile)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1599. Min Range: -2.1599

Max Act: 2.0022. Min Act: -0.0001

Data Index: 700449 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.8982. Min Act: -0.0001

Data Index: 564315 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.8705. Min Act: -0.0001

Data Index: 57788 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.9516. Min Act: -0.0001

Data Index: 921555 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7929. Min Act: -0.0001

Data Index: 709147 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7536. Min Act: -0.0001

Data Index: 1692405 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7729. Min Act: -0.0001

Data Index: 665699 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7261. Min Act: -0.0001

Data Index: 1921816 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7496. Min Act: -0.0001

Data Index: 1795196 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7809. Min Act: -0.0001

Data Index: 1772549 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7804. Min Act: -0.0001

Data Index: 964575 (The Pile)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7118. Min Act: -0.0001

Data Index: 1030011 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7531. Min Act: -0.0001

Data Index: 1152484 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.8210. Min Act: -0.0001

Data Index: 441145 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7776. Min Act: -0.0001

Data Index: 1815426 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7526. Min Act: -0.0001

Data Index: 1468278 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1599. Min Range: -2.1599

Max Act: 1.7909. Min Act: -0.0001

Data Index: 556052 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #19