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

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

Neuron 2446 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: 0.0285. Min Range: -0.0285

Max Act: 0.0267. Min Act: -0.0004

Data Index: 1506743 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1399055 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1509782 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0271. Min Act: -0.0004

Data Index: 1378006 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1607053 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1473760 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1583552 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1403858 (Python Code)

Max Activating Token Index: 33

Text #8

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0206. Min Act: -0.0004

Data Index: 1530932 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1598283 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1597891 (Python Code)

Max Activating Token Index: 921

Text #11

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1592198 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0219. Min Act: -0.0004

Data Index: 1432763 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0232. Min Act: -0.0004

Data Index: 1641142 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0180. Min Act: -0.0004

Data Index: 1590808 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1591517 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1586202 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1435699 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1382679 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0184. Min Act: -0.0004

Data Index: 1521142 (Python Code)

Max Activating Token Index: 321