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

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

Neuron 3 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1308137 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1621129 (Python Code)

Max Activating Token Index: 60

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1652357 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0207. Min Act: -0.0001

Data Index: 1449349 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0215. Min Act: -0.0001

Data Index: 404530 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0196. Min Act: -0.0001

Data Index: 385972 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1260155 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1408086 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0183. Min Act: -0.0001

Data Index: 750649 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0172. Min Act: -0.0001

Data Index: 278348 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0186. Min Act: -0.0001

Data Index: 284838 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1009536 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0187. Min Act: -0.0001

Data Index: 875937 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0166. Min Act: -0.0001

Data Index: 51149 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1377597 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1471414 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0177. Min Act: -0.0000

Data Index: 1416320 (Python Code)

Max Activating Token Index: 946

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1326657 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1015453 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1390795 (Python Code)

Max Activating Token Index: 803