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

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

Neuron 650 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0362. Min Act: -0.0001

Data Index: 826377 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0359. Min Act: -0.0001

Data Index: 140486 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1596663 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0373. Min Act: -0.0001

Data Index: 145695 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0382. Min Act: -0.0001

Data Index: 452533 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0359. Min Act: -0.0001

Data Index: 849383 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0386. Min Act: -0.0001

Data Index: 446895 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0332. Min Act: -0.0001

Data Index: 979105 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1313185 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1288577 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1624619 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0366. Min Act: -0.0001

Data Index: 45370 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0331. Min Act: -0.0001

Data Index: 742497 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0300. Min Act: -0.0001

Data Index: 209719 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0326. Min Act: -0.0001

Data Index: 933193 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1385416 (Python Code)

Max Activating Token Index: 558

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0317. Min Act: -0.0001

Data Index: 952768 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1328479 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0338. Min Act: -0.0001

Data Index: 110242 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0331. Min Act: -0.0001

Data Index: 58219 (C4 (Web Text))

Max Activating Token Index: 1016