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

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

Neuron 2997 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: 0.1390. Min Range: -0.1390

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1003529 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0002

Data Index: 929027 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1279. Min Act: -0.0003

Data Index: 662998 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1268. Min Act: -0.0003

Data Index: 210906 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1306. Min Act: -0.0002

Data Index: 137862 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1265. Min Act: -0.0003

Data Index: 793076 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1257. Min Act: -0.0003

Data Index: 533307 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1256. Min Act: -0.0003

Data Index: 365500 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1144. Min Act: -0.0003

Data Index: 1206109 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1236. Min Act: -0.0003

Data Index: 428916 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1280. Min Act: -0.0003

Data Index: 1201881 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1220. Min Act: -0.0002

Data Index: 897818 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1224. Min Act: -0.0003

Data Index: 583077 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1203. Min Act: -0.0002

Data Index: 770431 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1150. Min Act: -0.0003

Data Index: 973504 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1234. Min Act: -0.0003

Data Index: 36904 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1141. Min Act: -0.0003

Data Index: 1150909 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1141. Min Act: -0.0003

Data Index: 386108 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1104. Min Act: -0.0003

Data Index: 569850 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1179. Min Act: -0.0003

Data Index: 314898 (C4 (Web Text))

Max Activating Token Index: 248