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

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

Neuron 4581 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: 0.0299. Min Range: -0.0299

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1401519 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1450898 (Python Code)

Max Activating Token Index: 221

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1621892 (Python Code)

Max Activating Token Index: 487

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1384474 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1215541 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1385049 (Python Code)

Max Activating Token Index: 101

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1493445 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0261. Min Act: -0.0003

Data Index: 554395 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1503245 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1532257 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1517368 (Python Code)

Max Activating Token Index: 209

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1351171 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1479120 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1427349 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1564498 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1551806 (Python Code)

Max Activating Token Index: 265

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0270. Min Act: -0.0002

Data Index: 811717 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1504329 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1593469 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0258. Min Act: -0.0003

Data Index: 399757 (C4 (Web Text))

Max Activating Token Index: 691