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

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

Neuron 3529 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: 1.7536. Min Range: -1.7536

Max Act: 1.7536. Min Act: -0.0000

Data Index: 1611638 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1565832 (Python Code)

Max Activating Token Index: 207

Text #2

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1156220 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.2828. Min Act: -0.0000

Data Index: 1562480 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1061913 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1487739 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1420116 (Python Code)

Max Activating Token Index: 375

Text #7

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1628649 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1639090 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1405659 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0651. Min Act: -0.0000

Data Index: 66633 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1539147 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1489586 (Python Code)

Max Activating Token Index: 417

Text #13

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1497786 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1445444 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 1.7536. Min Range: -1.7536

Max Act: 0.9771. Min Act: -0.0000

Data Index: 856902 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.7536. Min Range: -1.7536

Max Act: 0.9680. Min Act: -0.0000

Data Index: 1421662 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 1.7536. Min Range: -1.7536

Max Act: 0.8849. Min Act: -0.0000

Data Index: 176999 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.7536. Min Range: -1.7536

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1613487 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 1.7536. Min Range: -1.7536

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1454316 (Python Code)

Max Activating Token Index: 971