Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2512 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0002

Data Index: 338219 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1630203 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0242. Min Act: -0.0002

Data Index: 272682 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1490258 (Python Code)

Max Activating Token Index: 454

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1523614 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0217. Min Act: -0.0002

Data Index: 441310 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0214. Min Act: -0.0002

Data Index: 417319 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1098537 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1494789 (Python Code)

Max Activating Token Index: 743

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1563159 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0194. Min Act: -0.0002

Data Index: 102188 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1525312 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1600129 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0193. Min Act: -0.0002

Data Index: 392226 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1526115 (Python Code)

Max Activating Token Index: 944

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1482567 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0181. Min Act: -0.0002

Data Index: 953941 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1605767 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0174. Min Act: -0.0002

Data Index: 91641 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1267722 (C4 (Web Text))

Max Activating Token Index: 532