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

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

Neuron 3692 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1034744 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1339521 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1756. Min Act: -0.0000

Data Index: 260194 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1751. Min Act: -0.0000

Data Index: 712531 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1588. Min Act: -0.0000

Data Index: 302794 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1603. Min Act: -0.0000

Data Index: 516976 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1344078 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1441. Min Act: -0.0000

Data Index: 912425 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1428. Min Act: -0.0000

Data Index: 312104 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1337. Min Act: -0.0000

Data Index: 119001 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1423. Min Act: -0.0000

Data Index: 362952 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1365. Min Act: -0.0000

Data Index: 956078 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1251. Min Act: -0.0000

Data Index: 477092 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1378. Min Act: -0.0000

Data Index: 734810 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1413. Min Act: -0.0000

Data Index: 258876 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1290. Min Act: -0.0000

Data Index: 720612 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1367. Min Act: -0.0000

Data Index: 783954 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1399. Min Act: -0.0000

Data Index: 815784 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1310. Min Act: -0.0000

Data Index: 698979 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1249. Min Act: -0.0000

Data Index: 465398 (C4 (Web Text))

Max Activating Token Index: 411