Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2313 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2532. Min Act: -0.0001

Data Index: 94521 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2698. Min Act: -0.0001

Data Index: 624578 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2221. Min Act: -0.0001

Data Index: 135882 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2297. Min Act: -0.0001

Data Index: 404144 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2720. Min Act: -0.0001

Data Index: 1253438 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2046. Min Act: -0.0001

Data Index: 174470 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2104. Min Act: -0.0001

Data Index: 951350 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2169. Min Act: -0.0001

Data Index: 271755 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2239. Min Act: -0.0001

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1945. Min Act: -0.0001

Data Index: 996835 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1167614 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2144. Min Act: -0.0001

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2263. Min Act: -0.0001

Data Index: 398207 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2145. Min Act: -0.0001

Data Index: 64214 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2112. Min Act: -0.0001

Data Index: 643325 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2068. Min Act: -0.0001

Data Index: 299639 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1211726 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2344. Min Act: -0.0001

Data Index: 828291 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.1902. Min Act: -0.0001

Data Index: 691408 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1335780 (C4 (Web Text))

Max Activating Token Index: 262