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

Dataset: The Pile

Neuron 516 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1832880 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1590766 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3804. Min Act: -0.0000

Data Index: 376092 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1076196 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3766. Min Act: -0.0000

Data Index: 1697061 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1728453 (The Pile)

Max Activating Token Index: 312

Text #6

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1780784 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3962. Min Act: -0.0000

Data Index: 223534 (The Pile)

Max Activating Token Index: 533

Text #8

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3457. Min Act: -0.0000

Data Index: 1733918 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.0916. Min Act: -0.0000

Data Index: 864817 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3470. Min Act: -0.0000

Data Index: 1369700 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.3003. Min Act: -0.0000

Data Index: 986607 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1836721 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.1964. Min Act: -0.0000

Data Index: 919071 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1051249 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.1422. Min Act: -0.0000

Data Index: 755475 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.1833. Min Act: 0.0000

Data Index: 1149033 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1853236 (The Pile)

Max Activating Token Index: 92

Text #18

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1766147 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.5664. Min Range: -1.5664

Max Act: 1.1980. Min Act: -0.0000

Data Index: 979326 (The Pile)

Max Activating Token Index: 614