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

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

Neuron 850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1287786 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0268. Min Act: -0.0003

Data Index: 169227 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0239. Min Act: -0.0003

Data Index: 632512 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1136959 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0003

Data Index: 773770 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1261971 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1040178 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1060489 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0213. Min Act: -0.0003

Data Index: 390279 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0214. Min Act: -0.0003

Data Index: 116752 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0218. Min Act: -0.0003

Data Index: 509719 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0217. Min Act: -0.0003

Data Index: 129599 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1601296 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0209. Min Act: -0.0003

Data Index: 482582 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1210706 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0203. Min Act: -0.0003

Data Index: 354600 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1475 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0202. Min Act: -0.0003

Data Index: 927956 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0209. Min Act: -0.0003

Data Index: 123112 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0194. Min Act: -0.0002

Data Index: 550407 (C4 (Web Text))

Max Activating Token Index: 971