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

Dataset: The Pile

Neuron 840 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: 1.4580. Min Range: -1.4580

Max Act: 1.4580. Min Act: -0.0000

Data Index: 947061 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2186. Min Act: -0.0000

Data Index: 54377 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1179879 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1877435 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0750. Min Act: -0.0000

Data Index: 697002 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1014. Min Act: -0.0000

Data Index: 103928 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1924665 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1775. Min Act: -0.0000

Data Index: 560777 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0003. Min Act: -0.0000

Data Index: 952729 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1404. Min Act: -0.0000

Data Index: 281433 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2019. Min Act: -0.0000

Data Index: 937372 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1204. Min Act: -0.0000

Data Index: 546518 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1716231 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1313203 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1272061 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.8955. Min Act: -0.0000

Data Index: 1361777 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1658127 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1622870 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 1.4580. Min Range: -1.4580

Max Act: 0.9247. Min Act: -0.0000

Data Index: 1118845 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1111217 (The Pile)

Max Activating Token Index: 753