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

Dataset: The Pile

Neuron 1777 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: 0.5173. Min Range: -0.5173

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1953382 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.5173. Min Act: -0.0000

Data Index: 37622 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4007. Min Act: -0.0000

Data Index: 252773 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1523369 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1113301 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.4147. Min Act: -0.0000

Data Index: 542539 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3291. Min Act: -0.0000

Data Index: 577500 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3374. Min Act: -0.0000

Data Index: 360799 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2198. Min Act: -0.0000

Data Index: 978879 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.3217. Min Act: -0.0000

Data Index: 143349 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1743386 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2354. Min Act: -0.0000

Data Index: 156622 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1146995 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1054999 (The Pile)

Max Activating Token Index: 70

Text #14

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1947208 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2366. Min Act: -0.0000

Data Index: 927338 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2628. Min Act: -0.0000

Data Index: 476533 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1765911 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1613848 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 0.5173. Min Range: -0.5173

Max Act: 0.2557. Min Act: -0.0000

Data Index: 745869 (The Pile)

Max Activating Token Index: 327