Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1364 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.3543. Min Act: -0.0003

Data Index: 222827 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2348. Min Act: -0.0003

Data Index: 1336990 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2333. Min Act: -0.0003

Data Index: 101007 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2402. Min Act: -0.0003

Data Index: 688425 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2374. Min Act: -0.0003

Data Index: 47482 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2453. Min Act: -0.0003

Data Index: 172246 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2336. Min Act: -0.0003

Data Index: 309092 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2386. Min Act: -0.0003

Data Index: 591819 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2288. Min Act: -0.0003

Data Index: 263223 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2279. Min Act: -0.0003

Data Index: 474233 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2182. Min Act: -0.0003

Data Index: 251816 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2242. Min Act: -0.0003

Data Index: 1149543 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2202. Min Act: -0.0003

Data Index: 207529 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2192. Min Act: -0.0003

Data Index: 1324677 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2125. Min Act: -0.0004

Data Index: 473436 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2184. Min Act: -0.0003

Data Index: 651703 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2177. Min Act: -0.0003

Data Index: 671315 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2249. Min Act: -0.0003

Data Index: 818856 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2157. Min Act: -0.0002

Data Index: 505742 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.3543. Min Range: -0.3543

Max Act: 0.2165. Min Act: -0.0003

Data Index: 641665 (C4 (Web Text))

Max Activating Token Index: 1004