Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2347 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.2447. Min Act: -0.0000

Data Index: 96912 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1617. Min Act: -0.0000

Data Index: 260922 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1622. Min Act: -0.0000

Data Index: 574909 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1495. Min Act: -0.0000

Data Index: 501164 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1418. Min Act: -0.0000

Data Index: 210773 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1658. Min Act: -0.0000

Data Index: 266460 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1203195 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1509. Min Act: -0.0000

Data Index: 748153 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1314179 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1107809 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1261749 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1392. Min Act: -0.0000

Data Index: 29546 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1487. Min Act: -0.0000

Data Index: 690360 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1515. Min Act: -0.0000

Data Index: 299468 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1046166 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1306. Min Act: -0.0000

Data Index: 292778 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1240962 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1589761 (Python Code)

Max Activating Token Index: 467

Text #18

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1386. Min Act: -0.0000

Data Index: 389787 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.2447. Min Range: -0.2447

Max Act: 0.1447. Min Act: -0.0000

Data Index: 662110 (C4 (Web Text))

Max Activating Token Index: 682