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

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

Neuron 4476 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1346847 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3049. Min Act: -0.0001

Data Index: 867862 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3262. Min Act: -0.0001

Data Index: 183311 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1106881 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1222343 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1328307 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1031278 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3159. Min Act: -0.0001

Data Index: 585123 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3041. Min Act: -0.0001

Data Index: 1051530 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3146. Min Act: -0.0001

Data Index: 235211 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2753. Min Act: -0.0001

Data Index: 861312 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1274986 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2861. Min Act: -0.0001

Data Index: 304533 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1222735 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2903. Min Act: -0.0001

Data Index: 604592 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2822. Min Act: -0.0001

Data Index: 867933 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2798. Min Act: -0.0001

Data Index: 397901 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2725. Min Act: -0.0001

Data Index: 121880 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1271829 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2563. Min Act: -0.0001

Data Index: 226589 (C4 (Web Text))

Max Activating Token Index: 815