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

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

Neuron 1908 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: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0002

Data Index: 468018 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0388. Min Act: -0.0002

Data Index: 85263 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1412743 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1458567 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0262. Min Act: -0.0002

Data Index: 92642 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1507531 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0241. Min Act: -0.0002

Data Index: 151116 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0258. Min Act: -0.0002

Data Index: 707096 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0245. Min Act: -0.0002

Data Index: 266347 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0249. Min Act: -0.0002

Data Index: 90847 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1312909 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1369566 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1409669 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1540602 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1118446 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1625321 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1462962 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1427401 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0231. Min Act: -0.0002

Data Index: 258206 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0222. Min Act: -0.0002

Data Index: 927191 (C4 (Web Text))

Max Activating Token Index: 506