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

Dataset: The Pile

Neuron 406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1465371 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1455. Min Act: -0.0000

Data Index: 309515 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0217. Min Act: -0.0000

Data Index: 769808 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.1265. Min Act: -0.0000

Data Index: 938126 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1034990 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1382136 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8944. Min Act: -0.0000

Data Index: 549162 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1981415 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9147. Min Act: -0.0000

Data Index: 622166 (The Pile)

Max Activating Token Index: 97

Text #9

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9147. Min Act: -0.0000

Data Index: 535330 (The Pile)

Max Activating Token Index: 974

Text #10

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9065. Min Act: -0.0000

Data Index: 587672 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1834612 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8330. Min Act: -0.0000

Data Index: 623104 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1309440 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9684. Min Act: -0.0000

Data Index: 1504331 (The Pile)

Max Activating Token Index: 1015

Text #15

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8531. Min Act: -0.0000

Data Index: 281879 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8651. Min Act: -0.0000

Data Index: 855649 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1017608 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1301699 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8515. Min Act: -0.0000

Data Index: 417325 (The Pile)

Max Activating Token Index: 352