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

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

Neuron 1348 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: 0.3251. Min Range: -0.3251

Max Act: 0.3251. Min Act: -0.0000

Data Index: 544190 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.3091. Min Act: -0.0000

Data Index: 505438 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2820. Min Act: -0.0000

Data Index: 461504 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2287. Min Act: -0.0000

Data Index: 518028 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2107. Min Act: -0.0000

Data Index: 429077 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2327. Min Act: -0.0000

Data Index: 70903 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1635025 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1948. Min Act: -0.0000

Data Index: 573150 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1804. Min Act: -0.0000

Data Index: 315326 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1940. Min Act: -0.0000

Data Index: 681197 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1848. Min Act: -0.0000

Data Index: 614093 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.2029. Min Act: -0.0000

Data Index: 214473 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1406960 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1260817 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1897. Min Act: -0.0000

Data Index: 782060 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1985. Min Act: -0.0000

Data Index: 995423 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1504378 (Python Code)

Max Activating Token Index: 943

Text #17

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1836. Min Act: -0.0000

Data Index: 177282 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1945. Min Act: -0.0000

Data Index: 99051 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.3251. Min Range: -0.3251

Max Act: 0.1707. Min Act: -0.0000

Data Index: 189039 (C4 (Web Text))

Max Activating Token Index: 788