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

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

Neuron 459 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: 0.0327. Min Range: -0.0327

Max Act: 0.0284. Min Act: -0.0002

Data Index: 753874 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0002

Data Index: 213524 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0298. Min Act: -0.0002

Data Index: 105978 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1194913 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1631739 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0278. Min Act: -0.0002

Data Index: 317659 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0269. Min Act: -0.0002

Data Index: 941718 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0002

Data Index: 315199 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0277. Min Act: -0.0002

Data Index: 199725 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1127989 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0278. Min Act: -0.0002

Data Index: 200757 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0283. Min Act: -0.0002

Data Index: 335610 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0002

Data Index: 287557 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0259. Min Act: -0.0002

Data Index: 223015 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1536323 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0214. Min Act: -0.0002

Data Index: 496665 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0002

Data Index: 340032 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1223779 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0241. Min Act: -0.0002

Data Index: 999989 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0239. Min Act: -0.0002

Data Index: 488250 (C4 (Web Text))

Max Activating Token Index: 298