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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2694 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0003

Data Index: 564861 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0230. Min Act: -0.0003

Data Index: 429061 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0240. Min Act: -0.0003

Data Index: 529688 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0229. Min Act: -0.0003

Data Index: 415268 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1565475 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0219. Min Act: -0.0003

Data Index: 429767 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0003

Data Index: 131919 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0226. Min Act: -0.0003

Data Index: 3408 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0206. Min Act: -0.0003

Data Index: 381316 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0211. Min Act: -0.0003

Data Index: 945034 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1624007 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0199. Min Act: -0.0003

Data Index: 712144 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0198. Min Act: -0.0003

Data Index: 150711 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0206. Min Act: -0.0003

Data Index: 432680 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1144068 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0199. Min Act: -0.0003

Data Index: 735414 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1390248 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0184. Min Act: -0.0003

Data Index: 105652 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1608998 (Python Code)

Max Activating Token Index: 628

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1497167 (Python Code)

Max Activating Token Index: 563