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

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

Neuron 17 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1163410 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2080. Min Act: -0.0000

Data Index: 670071 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1233011 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1891. Min Act: -0.0000

Data Index: 840693 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2049. Min Act: -0.0000

Data Index: 481676 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1955. Min Act: -0.0001

Data Index: 126277 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1028092 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1924. Min Act: -0.0000

Data Index: 464506 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1183018 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1954. Min Act: -0.0000

Data Index: 505533 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1935. Min Act: -0.0000

Data Index: 24049 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1869. Min Act: -0.0000

Data Index: 879594 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1909. Min Act: -0.0000

Data Index: 933592 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1070782 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1880. Min Act: -0.0000

Data Index: 438383 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1725. Min Act: -0.0000

Data Index: 381999 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1304492 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1750. Min Act: -0.0000

Data Index: 568989 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1877. Min Act: -0.0001

Data Index: 46440 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1633. Min Act: -0.0000

Data Index: 278207 (C4 (Web Text))

Max Activating Token Index: 552