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

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

Neuron 2582 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0001

Data Index: 830408 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1321422 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0221. Min Act: -0.0001

Data Index: 548314 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0205. Min Act: -0.0001

Data Index: 556878 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1644695 (Python Code)

Max Activating Token Index: 215

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0189. Min Act: -0.0001

Data Index: 1481179 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1479193 (Python Code)

Max Activating Token Index: 783

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1609774 (Python Code)

Max Activating Token Index: 943

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1333537 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1309528 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0187. Min Act: -0.0001

Data Index: 272581 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1535995 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1514365 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0153. Min Act: -0.0001

Data Index: 1233129 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1414104 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0170. Min Act: -0.0001

Data Index: 1524470 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0153. Min Act: -0.0001

Data Index: 103499 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1551172 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0140. Min Act: -0.0001

Data Index: 406865 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0160. Min Act: -0.0001

Data Index: 1379631 (Python Code)

Max Activating Token Index: 731