< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 10 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.7469. Min Act: -0.0000

Data Index: 807155 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.7084. Min Act: -0.0000

Data Index: 585319 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1377612 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6696. Min Act: -0.0000

Data Index: 187270 (The Pile)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6549. Min Act: -0.0000

Data Index: 122303 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6477. Min Act: -0.0000

Data Index: 413074 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1032145 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1324915 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1361251 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1092661 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6172. Min Act: -0.0000

Data Index: 121359 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1911725 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1721022 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.6003. Min Act: -0.0000

Data Index: 221498 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1681772 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.5714. Min Act: -0.0000

Data Index: 576924 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.5832. Min Act: -0.0000

Data Index: 619981 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1349495 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1014618 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.7469. Min Range: -0.7469

Max Act: 0.5975. Min Act: -0.0000

Data Index: 378122 (The Pile)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #19