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

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

Neuron 2053 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: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0000

Data Index: 644967 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1062711 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1394955 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1704. Min Act: -0.0001

Data Index: 753959 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1529465 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1648. Min Act: -0.0001

Data Index: 340701 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1641. Min Act: -0.0000

Data Index: 266896 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1266825 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1398806 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1481048 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1504917 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1469727 (Python Code)

Max Activating Token Index: 952

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1568896 (Python Code)

Max Activating Token Index: 687

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1215466 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1459. Min Act: -0.0000

Data Index: 780694 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1606920 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1196393 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1592348 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1419. Min Act: -0.0001

Data Index: 551487 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1415. Min Act: -0.0001

Data Index: 656868 (C4 (Web Text))

Max Activating Token Index: 635