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

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

Neuron 702 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0002

Data Index: 1373524 (Python Code)

Max Activating Token Index: 682

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1237. Min Act: -0.0002

Data Index: 1470198 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1374509 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1644928 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1531588 (Python Code)

Max Activating Token Index: 625

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1401158 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1634869 (Python Code)

Max Activating Token Index: 951

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1442051 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1102. Min Act: -0.0002

Data Index: 1384559 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1424097 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1552890 (Python Code)

Max Activating Token Index: 629

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1502160 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1497517 (Python Code)

Max Activating Token Index: 181

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1490041 (Python Code)

Max Activating Token Index: 592

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1578984 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1471565 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1475314 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1599433 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1567222 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1648161 (Python Code)

Max Activating Token Index: 415