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

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

Neuron 3004 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0002

Data Index: 899112 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0217. Min Act: -0.0002

Data Index: 31695 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0215. Min Act: -0.0002

Data Index: 560882 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1204051 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0207. Min Act: -0.0002

Data Index: 435700 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0204. Min Act: -0.0002

Data Index: 421918 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0207. Min Act: -0.0002

Data Index: 811582 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1268590 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0208. Min Act: -0.0002

Data Index: 555930 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0202. Min Act: -0.0002

Data Index: 63379 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1158387 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1001078 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0202. Min Act: -0.0002

Data Index: 669933 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0193. Min Act: -0.0002

Data Index: 609339 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1094752 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1209183 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0195. Min Act: -0.0002

Data Index: 266132 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0194. Min Act: -0.0002

Data Index: 5379 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0194. Min Act: -0.0002

Data Index: 27639 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0192. Min Act: -0.0002

Data Index: 206225 (C4 (Web Text))

Max Activating Token Index: 399