Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1868 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1400123 (Python Code)

Max Activating Token Index: 942

Text #1

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1899. Min Act: -0.0000

Data Index: 618519 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1971. Min Act: -0.0000

Data Index: 139487 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1503337 (Python Code)

Max Activating Token Index: 265

Text #4

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1734. Min Act: -0.0000

Data Index: 384216 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1714. Min Act: -0.0000

Data Index: 927398 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1855. Min Act: -0.0000

Data Index: 170178 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1815. Min Act: -0.0000

Data Index: 639532 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2011. Min Act: -0.0000

Data Index: 722112 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1075240 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1507753 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1619. Min Act: -0.0000

Data Index: 558081 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1426891 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1675. Min Act: -0.0000

Data Index: 398017 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1568402 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1145857 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1518. Min Act: -0.0000

Data Index: 820312 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1037547 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1605. Min Act: -0.0000

Data Index: 648996 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1424. Min Act: -0.0000

Data Index: 572936 (C4 (Web Text))

Max Activating Token Index: 328