Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3778 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0000

Data Index: 653413 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1384013 (Python Code)

Max Activating Token Index: 682

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1708. Min Act: -0.0000

Data Index: 874338 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1675. Min Act: -0.0000

Data Index: 6997 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1492672 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1280665 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1512. Min Act: -0.0001

Data Index: 660728 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1550. Min Act: -0.0000

Data Index: 794207 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1529. Min Act: -0.0001

Data Index: 964849 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1471810 (Python Code)

Max Activating Token Index: 828

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1456. Min Act: -0.0000

Data Index: 36919 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1392828 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1403. Min Act: -0.0000

Data Index: 170765 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1344. Min Act: -0.0000

Data Index: 638546 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1611844 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1292. Min Act: -0.0000

Data Index: 531330 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1318. Min Act: -0.0000

Data Index: 449178 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1446522 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1298. Min Act: -0.0001

Data Index: 853621 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1274699 (C4 (Web Text))

Max Activating Token Index: 215