< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4026 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0001

Data Index: 773422 (The Pile)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0900. Min Act: -0.0001

Data Index: 140926 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1480103 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1167912 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1557211 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1578822 (The Pile)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0756. Min Act: -0.0001

Data Index: 796250 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0730. Min Act: -0.0001

Data Index: 39280 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1718124 (The Pile)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1804743 (The Pile)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0704. Min Act: -0.0001

Data Index: 978775 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1137990 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1235943 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1158375 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1610723 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0695. Min Act: -0.0001

Data Index: 345581 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1145270 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1695746 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1462484 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0805. Min Act: -0.0001

Data Index: 1710380 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #19