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

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

Neuron 3962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0224. Min Act: -0.0002

Data Index: 253023 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1404902 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0204. Min Act: -0.0002

Data Index: 459439 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1565762 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1507999 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1565922 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1339994 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0170. Min Act: -0.0002

Data Index: 55180 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0163. Min Act: -0.0002

Data Index: 693711 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1441422 (Python Code)

Max Activating Token Index: 958

Text #10

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1245606 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1434572 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1406447 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1413667 (Python Code)

Max Activating Token Index: 76

Text #14

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0161. Min Act: -0.0002

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1451417 (Python Code)

Max Activating Token Index: 786

Text #16

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0136. Min Act: -0.0002

Data Index: 876387 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1323341 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1455257 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 0.0224. Min Range: -0.0224

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1483615 (Python Code)

Max Activating Token Index: 290