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

Dataset: The Pile

Neuron 1902 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1824. Min Act: -0.0000

Data Index: 115746 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.2439. Min Act: -0.0000

Data Index: 453188 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1094374 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.2087. Min Act: -0.0000

Data Index: 139195 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0859. Min Act: -0.0000

Data Index: 544056 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.2217. Min Act: -0.0000

Data Index: 510820 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1839. Min Act: -0.0000

Data Index: 583189 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1364845 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1366. Min Act: -0.0000

Data Index: 455253 (The Pile)

Max Activating Token Index: 629

Text #9

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0627. Min Act: -0.0000

Data Index: 402593 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1035337 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1163385 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1498143 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0509. Min Act: -0.0000

Data Index: 458023 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1773878 (The Pile)

Max Activating Token Index: 301

Text #15

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1155233 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1018. Min Act: -0.0000

Data Index: 357767 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1718913 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1192201 (The Pile)

Max Activating Token Index: 917

Text #19

Max Range: 1.2439. Min Range: -1.2439

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1561573 (The Pile)

Max Activating Token Index: 263