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

Dataset: The Pile

Neuron 796 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: 0.2745. Min Range: -0.2745

Max Act: 0.2745. Min Act: -0.0000

Data Index: 843265 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2646. Min Act: -0.0000

Data Index: 70706 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1809025 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1649771 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1197034 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2245. Min Act: -0.0000

Data Index: 328353 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1610288 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1812846 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2132. Min Act: -0.0000

Data Index: 205302 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2211. Min Act: -0.0000

Data Index: 505391 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2073. Min Act: -0.0000

Data Index: 167254 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1463485 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2234. Min Act: -0.0000

Data Index: 274268 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1739060 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2053. Min Act: -0.0000

Data Index: 422727 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2037. Min Act: -0.0000

Data Index: 352805 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1600212 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1579467 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1295325 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.2745. Min Range: -0.2745

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1868427 (The Pile)

Max Activating Token Index: 272