Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6128 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1068481 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0337. Min Act: -0.0002

Data Index: 772288 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0301. Min Act: -0.0002

Data Index: 336494 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1378644 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1630125 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1426174 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0226. Min Act: -0.0002

Data Index: 398692 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1515678 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1561072 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1389973 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0246. Min Act: -0.0002

Data Index: 204185 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1599679 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1435740 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1345070 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1634774 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0216. Min Act: -0.0002

Data Index: 794345 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1624209 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0209. Min Act: -0.0002

Data Index: 439438 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0250. Min Act: -0.0002

Data Index: 972057 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1445148 (Python Code)

Max Activating Token Index: 700