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

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

Neuron 4611 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.3111. Min Act: -0.0002

Data Index: 925196 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2379. Min Act: -0.0002

Data Index: 244612 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2362. Min Act: -0.0002

Data Index: 807642 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2097. Min Act: -0.0002

Data Index: 1112870 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2193. Min Act: -0.0002

Data Index: 441815 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2172. Min Act: -0.0002

Data Index: 767182 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2158. Min Act: -0.0002

Data Index: 479904 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2075. Min Act: -0.0002

Data Index: 72868 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2122. Min Act: -0.0002

Data Index: 247655 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2186. Min Act: -0.0002

Data Index: 519113 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2136. Min Act: -0.0002

Data Index: 574523 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2062. Min Act: -0.0002

Data Index: 6432 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2050. Min Act: -0.0002

Data Index: 858673 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2010. Min Act: -0.0002

Data Index: 1267249 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1932. Min Act: -0.0002

Data Index: 549563 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.2033. Min Act: -0.0002

Data Index: 412165 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1921. Min Act: -0.0002

Data Index: 1097971 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1954. Min Act: -0.0002

Data Index: 951331 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1896. Min Act: -0.0002

Data Index: 564804 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.3111. Min Range: -0.3111

Max Act: 0.1940. Min Act: -0.0002

Data Index: 1024327 (C4 (Web Text))

Max Activating Token Index: 590