Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 80 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0006

Data Index: 474352 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0387. Min Act: -0.0006

Data Index: 642876 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1022308 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1033913 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0377. Min Act: -0.0006

Data Index: 907899 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0381. Min Act: -0.0006

Data Index: 212301 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0373. Min Act: -0.0006

Data Index: 782569 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0367. Min Act: -0.0006

Data Index: 981689 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0006

Data Index: 53128 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0356. Min Act: -0.0006

Data Index: 268338 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0362. Min Act: -0.0006

Data Index: 117308 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0361. Min Act: -0.0006

Data Index: 1212768 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0373. Min Act: -0.0006

Data Index: 737809 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0357. Min Act: -0.0006

Data Index: 1161710 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0349. Min Act: -0.0006

Data Index: 99078 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0364. Min Act: -0.0006

Data Index: 70061 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0364. Min Act: -0.0006

Data Index: 1288876 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0342. Min Act: -0.0006

Data Index: 392474 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0328. Min Act: -0.0006

Data Index: 355995 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0360. Min Act: -0.0006

Data Index: 84588 (C4 (Web Text))

Max Activating Token Index: 511