Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1682 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0459. Min Act: -0.0004

Data Index: 658609 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0416. Min Act: -0.0004

Data Index: 1313983 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0423. Min Act: -0.0004

Data Index: 728618 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0449. Min Act: -0.0004

Data Index: 364489 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0416. Min Act: -0.0004

Data Index: 1057796 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0440. Min Act: -0.0004

Data Index: 328389 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0351. Min Act: -0.0004

Data Index: 864051 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0424. Min Act: -0.0004

Data Index: 1342652 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0379. Min Act: -0.0004

Data Index: 504589 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0371. Min Act: -0.0004

Data Index: 49683 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0364. Min Act: -0.0004

Data Index: 988298 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0343. Min Act: -0.0004

Data Index: 763904 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0363. Min Act: -0.0004

Data Index: 900784 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0392. Min Act: -0.0004

Data Index: 808896 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1192120 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0373. Min Act: -0.0004

Data Index: 510332 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0387. Min Act: -0.0004

Data Index: 478697 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0346. Min Act: -0.0004

Data Index: 593882 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0366. Min Act: -0.0004

Data Index: 530558 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0386. Min Act: -0.0004

Data Index: 397430 (C4 (Web Text))

Max Activating Token Index: 672