Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1367 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0003

Data Index: 277709 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1010247 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0251. Min Act: -0.0003

Data Index: 600912 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1444529 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0258. Min Act: -0.0003

Data Index: 837830 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1406211 (Python Code)

Max Activating Token Index: 539

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1364745 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0248. Min Act: -0.0003

Data Index: 346770 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1520856 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0236. Min Act: -0.0002

Data Index: 338796 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0232. Min Act: -0.0003

Data Index: 40320 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1635495 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1553967 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1470742 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1431957 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1514074 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1589069 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1418812 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1337552 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1396463 (Python Code)

Max Activating Token Index: 521