Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2755 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0004

Data Index: 1630727 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0308. Min Act: -0.0004

Data Index: 231439 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0291. Min Act: -0.0004

Data Index: 900182 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0307. Min Act: -0.0004

Data Index: 1613487 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0281. Min Act: -0.0004

Data Index: 1445243 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1569345 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1566424 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1459991 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0278. Min Act: -0.0004

Data Index: 352265 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0293. Min Act: -0.0004

Data Index: 191788 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0004

Data Index: 1077493 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1477897 (Python Code)

Max Activating Token Index: 996

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0276. Min Act: -0.0004

Data Index: 1604669 (Python Code)

Max Activating Token Index: 446

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0267. Min Act: -0.0004

Data Index: 1118026 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0276. Min Act: -0.0004

Data Index: 1596736 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1379880 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1628019 (Python Code)

Max Activating Token Index: 522

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0279. Min Act: -0.0004

Data Index: 349007 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0210. Min Act: -0.0004

Data Index: 1471546 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0263. Min Act: -0.0004

Data Index: 1492113 (Python Code)

Max Activating Token Index: 447