Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1714 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1356. Min Act: -0.0002

Data Index: 1590328 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1599610 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1471241 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1589922 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1649542 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1557768 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1176. Min Act: -0.0002

Data Index: 1503940 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1415751 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1468710 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1570724 (Python Code)

Max Activating Token Index: 688

Text #10

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1469854 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1511221 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1603056 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1485141 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1372810 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1572914 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1397656 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1388403 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1389093 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 0.1356. Min Range: -0.1356

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1538891 (Python Code)

Max Activating Token Index: 395