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

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

Neuron 1948 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: 0.0388. Min Range: -0.0388

Max Act: 0.0387. Min Act: -0.0003

Data Index: 736950 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0380. Min Act: -0.0003

Data Index: 76619 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1015183 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0372. Min Act: -0.0003

Data Index: 626119 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0374. Min Act: -0.0004

Data Index: 651131 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0003

Data Index: 4688 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0373. Min Act: -0.0003

Data Index: 659296 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0367. Min Act: -0.0004

Data Index: 1156836 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0374. Min Act: -0.0003

Data Index: 679380 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0359. Min Act: -0.0004

Data Index: 300836 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0372. Min Act: -0.0003

Data Index: 479307 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0357. Min Act: -0.0003

Data Index: 210130 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0349. Min Act: -0.0003

Data Index: 204596 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0355. Min Act: -0.0003

Data Index: 929435 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1341659 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0347. Min Act: -0.0003

Data Index: 462602 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0352. Min Act: -0.0003

Data Index: 140234 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0341. Min Act: -0.0002

Data Index: 832361 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1283571 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0349. Min Act: -0.0002

Data Index: 270414 (C4 (Web Text))

Max Activating Token Index: 436