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

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

Neuron 3251 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1623. Min Range: -2.1623

Max Act: 2.0902. Min Act: -0.0000

Data Index: 1527608 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 2.1623. Min Range: -2.1623

Max Act: 2.0668. Min Act: -0.0000

Data Index: 1432426 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 2.1623. Min Range: -2.1623

Max Act: 2.1623. Min Act: -0.0000

Data Index: 1653722 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 2.1623. Min Range: -2.1623

Max Act: 2.0914. Min Act: -0.0000

Data Index: 1456481 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.9169. Min Act: -0.0000

Data Index: 1507741 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.7369. Min Act: -0.0000

Data Index: 1363785 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.6845. Min Act: -0.0000

Data Index: 776566 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.6256. Min Act: -0.0000

Data Index: 1486231 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.4977. Min Act: -0.0000

Data Index: 52327 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.5966. Min Act: -0.0000

Data Index: 886607 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1491672 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1420181 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1502116 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.4124. Min Act: -0.0000

Data Index: 1514488 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.4197. Min Act: -0.0000

Data Index: 337258 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1409080 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1478869 (Python Code)

Max Activating Token Index: 706

Text #17

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1364973 (Python Code)

Max Activating Token Index: 563

Text #18

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1525444 (Python Code)

Max Activating Token Index: 727

Text #19

Max Range: 2.1623. Min Range: -2.1623

Max Act: 1.3502. Min Act: -0.0000

Data Index: 1370729 (Python Code)

Max Activating Token Index: 115