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

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

Neuron 3426 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1580. Min Act: -0.0001

Data Index: 364659 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1470132 (Python Code)

Max Activating Token Index: 587

Text #2

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1459620 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1518. Min Act: -0.0000

Data Index: 290719 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1546285 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1604763 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1453099 (Python Code)

Max Activating Token Index: 148

Text #7

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1600550 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1226392 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1623407 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1437744 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1564033 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1086585 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1550454 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1565190 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1400613 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1369916 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1384681 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1510980 (Python Code)

Max Activating Token Index: 981

Text #19

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1652007 (Python Code)

Max Activating Token Index: 186