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

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

Neuron 3592 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: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0003

Data Index: 229706 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1303271 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0248. Min Act: -0.0003

Data Index: 586313 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0251. Min Act: -0.0003

Data Index: 547984 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1517440 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1643762 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1569399 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0253. Min Act: -0.0002

Data Index: 220385 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1427542 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1024951 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1224476 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1603983 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0222. Min Act: -0.0002

Data Index: 757807 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0226. Min Act: -0.0003

Data Index: 185023 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0216. Min Act: -0.0003

Data Index: 635331 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1504625 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0224. Min Act: -0.0003

Data Index: 163722 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1633025 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1489550 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1643747 (Python Code)

Max Activating Token Index: 51