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

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

Neuron 3092 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8830. Min Act: -0.0000

Data Index: 1375840 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1477528 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1424656 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1478508 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1580606 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1625305 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1399530 (Python Code)

Max Activating Token Index: 675

Text #7

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1611966 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1557995 (Python Code)

Max Activating Token Index: 129

Text #9

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1438315 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1417027 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1464495 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1568084 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1504063 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1595324 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1393880 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1656276 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1630291 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1545871 (Python Code)

Max Activating Token Index: 414

Text #19

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7390. Min Act: -0.0001

Data Index: 1439745 (Python Code)

Max Activating Token Index: 761