< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4041 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: 3.5819. Min Range: -3.5819

Max Act: 3.5217. Min Act: -0.0001

Data Index: 748974 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5819. Min Range: -3.5819

Max Act: 3.5819. Min Act: -0.0001

Data Index: 280645 (The Pile)

Max Activating Token Index: 16

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5819. Min Range: -3.5819

Max Act: 3.0611. Min Act: -0.0001

Data Index: 112375 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5819. Min Range: -3.5819

Max Act: 3.0077. Min Act: -0.0001

Data Index: 835861 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.8041. Min Act: -0.0001

Data Index: 1534713 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.6717. Min Act: -0.0001

Data Index: 553538 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.7683. Min Act: -0.0001

Data Index: 1872816 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.7351. Min Act: -0.0001

Data Index: 250653 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.5788. Min Act: -0.0001

Data Index: 768477 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.7317. Min Act: -0.0001

Data Index: 209487 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.6827. Min Act: -0.0001

Data Index: 517402 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.6671. Min Act: -0.0001

Data Index: 1424378 (The Pile)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.6027. Min Act: -0.0001

Data Index: 1553011 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.4148. Min Act: -0.0001

Data Index: 63993 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.4894. Min Act: -0.0000

Data Index: 1507175 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.4830. Min Act: -0.0001

Data Index: 1110777 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.2529. Min Act: -0.0001

Data Index: 987500 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.4076. Min Act: -0.0001

Data Index: 51529 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.4999. Min Act: -0.0001

Data Index: 31965 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.3994. Min Act: -0.0001

Data Index: 410969 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #19