Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0003

Data Index: 804581 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0397. Min Act: -0.0003

Data Index: 398781 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0394. Min Act: -0.0003

Data Index: 336725 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0404. Min Act: -0.0004

Data Index: 986501 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0363. Min Act: -0.0004

Data Index: 788046 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1133451 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0363. Min Act: -0.0003

Data Index: 381594 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0346. Min Act: -0.0003

Data Index: 925308 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0356. Min Act: -0.0003

Data Index: 668597 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1328598 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1048911 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1234144 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0329. Min Act: -0.0004

Data Index: 361628 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0324. Min Act: -0.0003

Data Index: 354305 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1200140 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0322. Min Act: -0.0004

Data Index: 815911 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1328051 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0323. Min Act: -0.0004

Data Index: 569168 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0296. Min Act: -0.0003

Data Index: 886502 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0300. Min Act: -0.0003

Data Index: 916938 (C4 (Web Text))

Max Activating Token Index: 626