Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2468 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.4041. Min Range: -2.4041

Max Act: 2.3529. Min Act: -0.0000

Data Index: 359676 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 2.4041. Min Range: -2.4041

Max Act: 2.4041. Min Act: -0.0000

Data Index: 13327 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.8332. Min Act: -0.0000

Data Index: 658231 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.4551. Min Act: -0.0001

Data Index: 1499768 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.2100. Min Act: -0.0001

Data Index: 267187 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.4030. Min Act: -0.0001

Data Index: 771861 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.2416. Min Act: -0.0000

Data Index: 1355875 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1539055 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.0400. Min Act: -0.0000

Data Index: 22727 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.2040. Min Act: -0.0001

Data Index: 1598896 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.1908. Min Act: -0.0001

Data Index: 1654192 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.0485. Min Act: -0.0001

Data Index: 1592118 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1027571 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.4041. Min Range: -2.4041

Max Act: 0.9711. Min Act: -0.0001

Data Index: 566004 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.1218. Min Act: -0.0001

Data Index: 1618769 (Python Code)

Max Activating Token Index: 897

Text #15

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.2104. Min Act: -0.0001

Data Index: 1412374 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.1359. Min Act: -0.0001

Data Index: 43266 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.1065. Min Act: -0.0001

Data Index: 1437524 (Python Code)

Max Activating Token Index: 874

Text #18

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.0119. Min Act: -0.0001

Data Index: 1528520 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 2.4041. Min Range: -2.4041

Max Act: 1.0035. Min Act: -0.0001

Data Index: 1368551 (Python Code)

Max Activating Token Index: 115