< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4091 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: 1.4999. Min Range: -1.4999

Max Act: 1.4999. Min Act: -0.0001

Data Index: 1526336 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.2538. Min Act: -0.0001

Data Index: 172285 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.2069. Min Act: -0.0001

Data Index: 1570916 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.2221. Min Act: -0.0001

Data Index: 980020 (The Pile)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.1092. Min Act: -0.0001

Data Index: 1839346 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.1357. Min Act: -0.0001

Data Index: 541343 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.1997. Min Act: -0.0001

Data Index: 1050229 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.1198. Min Act: -0.0001

Data Index: 1268544 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0856. Min Act: -0.0001

Data Index: 1428595 (The Pile)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.1092. Min Act: -0.0001

Data Index: 1318921 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0445. Min Act: -0.0001

Data Index: 431488 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0751. Min Act: -0.0001

Data Index: 1907613 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1990518 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.4999. Min Range: -1.4999

Max Act: 0.9907. Min Act: -0.0001

Data Index: 1328055 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0155. Min Act: -0.0001

Data Index: 110977 (The Pile)

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0444. Min Act: -0.0001

Data Index: 1503837 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0454. Min Act: -0.0001

Data Index: 402416 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0321. Min Act: -0.0001

Data Index: 1125494 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0358. Min Act: -0.0001

Data Index: 164130 (The Pile)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.4999. Min Range: -1.4999

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1336805 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #19