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

Dataset: The Pile

Neuron 4278 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: 1.4531. Min Range: -1.4531

Max Act: 1.3232. Min Act: -0.0000

Data Index: 538872 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1085418 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1296923 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1794432 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.3509. Min Act: -0.0000

Data Index: 722049 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.1976. Min Act: -0.0000

Data Index: 538081 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1259416 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.1736. Min Act: -0.0000

Data Index: 585891 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1284533 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1413112 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0891. Min Act: -0.0000

Data Index: 162882 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0658. Min Act: -0.0000

Data Index: 63761 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1894032 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1122977 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1856988 (The Pile)

Max Activating Token Index: 933

Text #15

Max Range: 1.4531. Min Range: -1.4531

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1505807 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9623. Min Act: -0.0000

Data Index: 1294407 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1821619 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1832386 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 1.4531. Min Range: -1.4531

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1514219 (The Pile)

Max Activating Token Index: 370