< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4025 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: 0.9707. Min Range: -0.9707

Max Act: 0.9164. Min Act: -0.0001

Data Index: 1229729 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8471. Min Act: -0.0001

Data Index: 406123 (The Pile)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9707. Min Act: -0.0001

Data Index: 315312 (The Pile)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9173. Min Act: -0.0001

Data Index: 1118790 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7910. Min Act: -0.0001

Data Index: 1492546 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1697604 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9127. Min Act: -0.0001

Data Index: 547755 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9134. Min Act: -0.0001

Data Index: 434177 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9389. Min Act: -0.0001

Data Index: 1064081 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7176. Min Act: -0.0001

Data Index: 270825 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1862161 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8606. Min Act: -0.0001

Data Index: 354388 (The Pile)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9481. Min Act: -0.0001

Data Index: 1560916 (The Pile)

Max Activating Token Index: 316

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9217. Min Act: -0.0001

Data Index: 657161 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8899. Min Act: -0.0001

Data Index: 880953 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8421. Min Act: -0.0001

Data Index: 1901495 (The Pile)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8924. Min Act: -0.0001

Data Index: 1086536 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.6269. Min Act: -0.0002

Data Index: 1193923 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7515. Min Act: -0.0001

Data Index: 1243307 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9210. Min Act: -0.0001

Data Index: 1277572 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #19