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

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

Neuron 1705 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1605790 (Python Code)

Max Activating Token Index: 467

Text #1

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1168481 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0210. Min Act: -0.0003

Data Index: 820102 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1594845 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0184. Min Act: -0.0003

Data Index: 225422 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1628176 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1490616 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1576600 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1016353 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1421755 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1180667 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1639592 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1403890 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1085472 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1554144 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0177. Min Act: -0.0003

Data Index: 470676 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1242381 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1516984 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0165. Min Act: -0.0003

Data Index: 464334 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0215. Min Range: -0.0215

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1649980 (Python Code)

Max Activating Token Index: 41