Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1928073 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5844. Min Act: -0.0000

Data Index: 294217 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1407848 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5848. Min Act: -0.0000

Data Index: 377950 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5075. Min Act: -0.0000

Data Index: 308585 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1148818 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1030630 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4750. Min Act: -0.0000

Data Index: 205322 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4791. Min Act: -0.0000

Data Index: 951240 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.3550. Min Act: -0.0000

Data Index: 72653 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1510041 (The Pile)

Max Activating Token Index: 971

Text #11

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1191259 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4290. Min Act: -0.0000

Data Index: 172992 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1375445 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1172605 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1064337 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1557442 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4202. Min Act: -0.0000

Data Index: 727448 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1484112 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.6222. Min Range: -0.6222

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1053777 (The Pile)

Max Activating Token Index: 557