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

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

Neuron 3986 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1775. Min Act: 0.0000

Data Index: 917935 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1556. Min Act: -0.0000

Data Index: 160606 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1729. Min Act: -0.0000

Data Index: 88195 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1550. Min Act: -0.0000

Data Index: 904185 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1610. Min Act: -0.0000

Data Index: 866460 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1595. Min Act: -0.0000

Data Index: 702828 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1614. Min Act: -0.0000

Data Index: 997873 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1110857 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1572. Min Act: -0.0000

Data Index: 471722 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1138933 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1484. Min Act: -0.0000

Data Index: 787303 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1527. Min Act: 0.0000

Data Index: 779078 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1385. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1478. Min Act: -0.0000

Data Index: 116771 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1275. Min Act: -0.0000

Data Index: 298449 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1378. Min Act: -0.0000

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1341. Min Act: -0.0000

Data Index: 525137 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1120558 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1361. Min Act: 0.0000

Data Index: 935259 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1775. Min Range: -0.1775

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1543251 (Python Code)

Max Activating Token Index: 428