Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1620984 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0234. Min Act: -0.0001

Data Index: 675626 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0237. Min Act: -0.0001

Data Index: 770589 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1653334 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1408492 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1090824 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0197. Min Act: -0.0001

Data Index: 13115 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1372929 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0200. Min Act: -0.0001

Data Index: 555818 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1500813 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0193. Min Act: -0.0001

Data Index: 781773 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1586960 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1367871 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1023745 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1398790 (Python Code)

Max Activating Token Index: 39

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1366478 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0200. Min Act: -0.0001

Data Index: 1374247 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1137620 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1502643 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1649152 (Python Code)

Max Activating Token Index: 30