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

Dataset: The Pile

Neuron 1718 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.7212. Min Act: -0.0000

Data Index: 1238942 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1901866 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1019208 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1703151 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.2399. Min Act: -0.0000

Data Index: 715443 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.3227. Min Act: 0.0000

Data Index: 973795 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1589888 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.2329. Min Act: 0.0000

Data Index: 1598973 (The Pile)

Max Activating Token Index: 582

Text #8

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.1955. Min Act: -0.0000

Data Index: 64214 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.0904. Min Act: 0.0000

Data Index: 1202701 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.0074. Min Act: -0.0000

Data Index: 978337 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1324293 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1934664 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.1500. Min Act: -0.0000

Data Index: 894044 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.1646. Min Act: -0.0000

Data Index: 512849 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.0583. Min Act: -0.0000

Data Index: 604625 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.1122. Min Act: 0.0000

Data Index: 1624723 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1299470 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 1.7212. Min Range: -1.7212

Max Act: 1.0086. Min Act: -0.0000

Data Index: 707079 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 1.7212. Min Range: -1.7212

Max Act: 0.9980. Min Act: 0.0000

Data Index: 1345207 (The Pile)

Max Activating Token Index: 952