< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 2392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7051. Min Act: -0.0001

Data Index: 137957 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6928. Min Act: -0.0001

Data Index: 1627633 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6767. Min Act: -0.0002

Data Index: 393917 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6399. Min Act: -0.0001

Data Index: 1708147 (The Pile)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6446. Min Act: -0.0001

Data Index: 1855697 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1478554 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6601. Min Act: -0.0001

Data Index: 1637330 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6179. Min Act: -0.0001

Data Index: 38830 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6564. Min Act: -0.0001

Data Index: 829606 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6274. Min Act: -0.0001

Data Index: 1383035 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6148. Min Act: -0.0001

Data Index: 1449 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1634927 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6211. Min Act: -0.0001

Data Index: 1787391 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6130. Min Act: -0.0001

Data Index: 1756016 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6119. Min Act: -0.0002

Data Index: 1186379 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5495. Min Act: -0.0001

Data Index: 955268 (The Pile)

Max Activating Token Index: 837

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5940. Min Act: -0.0001

Data Index: 750360 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5705. Min Act: -0.0001

Data Index: 721366 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5551. Min Act: -0.0001

Data Index: 1360251 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5880. Min Act: -0.0002

Data Index: 252219 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #19