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

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

Neuron 4488 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: 0.0553. Min Range: -0.0553

Max Act: 0.0553. Min Act: -0.0002

Data Index: 288036 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0435. Min Act: -0.0002

Data Index: 409971 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1075250 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0415. Min Act: -0.0002

Data Index: 994754 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0413. Min Act: -0.0002

Data Index: 114635 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0415. Min Act: -0.0002

Data Index: 60607 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0401. Min Act: -0.0002

Data Index: 328059 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0383. Min Act: -0.0001

Data Index: 157631 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0396. Min Act: -0.0002

Data Index: 740479 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0378. Min Act: -0.0002

Data Index: 877102 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0378. Min Act: -0.0002

Data Index: 232919 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0377. Min Act: -0.0002

Data Index: 624870 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0386. Min Act: -0.0002

Data Index: 504997 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0358. Min Act: -0.0002

Data Index: 934905 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1307564 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0354. Min Act: -0.0002

Data Index: 763948 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1002245 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1056014 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0364. Min Act: -0.0002

Data Index: 817929 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.0553. Min Range: -0.0553

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1148546 (C4 (Web Text))

Max Activating Token Index: 56