< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 9 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.8828. Min Act: -0.0000

Data Index: 87477 (The Pile)

Max Activating Token Index: 894

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1106970 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0624. Min Range: -1.0624

Max Act: 1.0624. Min Act: -0.0001

Data Index: 1057708 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.9116. Min Act: -0.0001

Data Index: 994200 (The Pile)

Max Activating Token Index: 302

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.8999. Min Act: -0.0001

Data Index: 1624496 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7231. Min Act: -0.0001

Data Index: 267161 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7107. Min Act: -0.0001

Data Index: 1342811 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.8649. Min Act: -0.0001

Data Index: 50526 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0624. Min Range: -1.0624

Max Act: 1.0282. Min Act: -0.0000

Data Index: 945238 (The Pile)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7839. Min Act: -0.0001

Data Index: 1283119 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1783143 (The Pile)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7027. Min Act: -0.0001

Data Index: 522859 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7281. Min Act: -0.0001

Data Index: 1428289 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1831895 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.6524. Min Act: -0.0001

Data Index: 174364 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.7061. Min Act: -0.0001

Data Index: 1743304 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.6229. Min Act: -0.0001

Data Index: 1506314 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.6273. Min Act: -0.0001

Data Index: 1638247 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.6554. Min Act: -0.0001

Data Index: 330712 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0624. Min Range: -1.0624

Max Act: 0.6171. Min Act: -0.0000

Data Index: 545903 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #19