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

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

Neuron 242 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0000

Data Index: 73784 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0291. Min Act: -0.0000

Data Index: 299213 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1128173 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0238. Min Act: -0.0000

Data Index: 840744 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0233. Min Act: -0.0000

Data Index: 84105 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1209976 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0217. Min Act: -0.0000

Data Index: 660561 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0228. Min Act: -0.0000

Data Index: 187927 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0220. Min Act: -0.0000

Data Index: 233222 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0209. Min Act: -0.0000

Data Index: 994776 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0208. Min Act: -0.0000

Data Index: 107675 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0215. Min Act: -0.0000

Data Index: 480120 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0213. Min Act: -0.0000

Data Index: 1176588 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0222. Min Act: -0.0000

Data Index: 1243069 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0210. Min Act: -0.0000

Data Index: 982888 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0219. Min Act: -0.0000

Data Index: 722837 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0209. Min Act: -0.0000

Data Index: 219666 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0210. Min Act: -0.0000

Data Index: 402710 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1045270 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0206. Min Act: -0.0000

Data Index: 53503 (C4 (Web Text))

Max Activating Token Index: 309