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

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

Neuron 3546 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: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0003

Data Index: 173664 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0534. Min Act: -0.0003

Data Index: 54199 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0300. Min Act: -0.0002

Data Index: 556132 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0336. Min Act: -0.0003

Data Index: 912676 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0201. Min Act: -0.0003

Data Index: 528087 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1612063 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0313. Min Act: -0.0002

Data Index: 590805 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1048719 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0243. Min Act: -0.0003

Data Index: 328162 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0277. Min Act: -0.0002

Data Index: 687034 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0319. Min Act: -0.0002

Data Index: 363187 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0305. Min Act: -0.0003

Data Index: 960460 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0225. Min Act: -0.0003

Data Index: 121365 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0192. Min Act: -0.0003

Data Index: 157410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1319250 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1183356 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0248. Min Act: -0.0002

Data Index: 507218 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0192. Min Act: -0.0003

Data Index: 838669 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0256. Min Act: -0.0003

Data Index: 211562 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0233. Min Act: -0.0003

Data Index: 132383 (C4 (Web Text))

Max Activating Token Index: 472