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

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

Neuron 1925 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: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0003

Data Index: 842479 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0414. Min Act: -0.0003

Data Index: 919152 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1042734 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1130383 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1626426 (Python Code)

Max Activating Token Index: 631

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1348674 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1407627 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1594242 (Python Code)

Max Activating Token Index: 755

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1440619 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0381. Min Act: -0.0003

Data Index: 171257 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0383. Min Act: -0.0003

Data Index: 370435 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1407062 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1428535 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1114910 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0376. Min Act: -0.0004

Data Index: 550579 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1485174 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1623438 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1137070 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1502790 (Python Code)

Max Activating Token Index: 420

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1616416 (Python Code)

Max Activating Token Index: 311