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

Dataset: The Pile

Neuron 2272 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1064981 (The Pile)

Max Activating Token Index: 376

Text #1

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1821255 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1072150 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1925503 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3290. Min Act: -0.0000

Data Index: 762774 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1679899 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1452876 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1735369 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3872. Min Act: -0.0000

Data Index: 620151 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1229440 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1424298 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.1954. Min Act: -0.0000

Data Index: 879607 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3432. Min Act: -0.0000

Data Index: 130288 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.2748. Min Act: -0.0000

Data Index: 720188 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1043430 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1166757 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1945162 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1242745 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1287263 (The Pile)

Max Activating Token Index: 382

Text #19

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1396355 (The Pile)

Max Activating Token Index: 947