Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 26 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1550. Min Act: -0.0001

Data Index: 862319 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1566. Min Act: -0.0000

Data Index: 287558 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1235513 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1543. Min Act: -0.0001

Data Index: 809499 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1471. Min Act: -0.0000

Data Index: 671400 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1490. Min Act: -0.0000

Data Index: 979939 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1403. Min Act: -0.0000

Data Index: 62308 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1445. Min Act: -0.0001

Data Index: 657021 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1020393 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1427. Min Act: -0.0000

Data Index: 919882 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1157971 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1207591 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1152812 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1327. Min Act: -0.0001

Data Index: 124164 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1194517 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1377. Min Act: -0.0001

Data Index: 550483 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1080413 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1448. Min Act: -0.0001

Data Index: 610496 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1249816 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1347. Min Act: -0.0000

Data Index: 940911 (C4 (Web Text))

Max Activating Token Index: 322