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

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

Neuron 4807 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: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0002

Data Index: 1437511 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1624647 (Python Code)

Max Activating Token Index: 384

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1635232 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1259. Min Act: -0.0002

Data Index: 1377801 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1215. Min Act: -0.0002

Data Index: 1129107 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1129. Min Act: -0.0002

Data Index: 515832 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1249. Min Act: -0.0002

Data Index: 28796 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1157. Min Act: -0.0002

Data Index: 151298 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1131. Min Act: -0.0002

Data Index: 949209 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1162. Min Act: -0.0002

Data Index: 603614 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1174. Min Act: -0.0002

Data Index: 228572 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1544914 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1471691 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1645329 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1569597 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1505130 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1274869 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1361397 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1418490 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1560868 (Python Code)

Max Activating Token Index: 368