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

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

Neuron 1946 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.2720. Min Act: -0.0000

Data Index: 1118339 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1275828 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.2720. Min Range: -1.2720

Max Act: 1.0368. Min Act: -0.0000

Data Index: 624602 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9690. Min Act: -0.0000

Data Index: 659572 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9745. Min Act: -0.0000

Data Index: 147464 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1450173 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1319621 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1286762 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9281. Min Act: -0.0000

Data Index: 574286 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.9170. Min Act: -0.0000

Data Index: 132764 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1337720 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8668. Min Act: -0.0000

Data Index: 204249 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1028452 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1537978 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1061929 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1544838 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8575. Min Act: -0.0000

Data Index: 104477 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7897. Min Act: -0.0000

Data Index: 660041 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1254577 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 1.2720. Min Range: -1.2720

Max Act: 0.7741. Min Act: -0.0000

Data Index: 2234 (C4 (Web Text))

Max Activating Token Index: 594