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

Dataset: The Pile

Neuron 1410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 246174 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2210. Min Act: -0.0000

Data Index: 142526 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2074. Min Act: -0.0000

Data Index: 885681 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2070. Min Act: -0.0000

Data Index: 428415 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2072. Min Act: -0.0000

Data Index: 374253 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1190398 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2079. Min Act: -0.0000

Data Index: 732969 (The Pile)

Max Activating Token Index: 533

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1992. Min Act: -0.0000

Data Index: 554492 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1840. Min Act: -0.0000

Data Index: 899711 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1897. Min Act: -0.0000

Data Index: 341906 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1986. Min Act: -0.0000

Data Index: 273632 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1995. Min Act: -0.0000

Data Index: 993228 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1650465 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1681795 (The Pile)

Max Activating Token Index: 258

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1756. Min Act: -0.0000

Data Index: 727720 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1623. Min Act: -0.0000

Data Index: 630180 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1236359 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1767. Min Act: -0.0000

Data Index: 1979475 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1487948 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1789860 (The Pile)

Max Activating Token Index: 20