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

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

Neuron 913 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: 0.2548. Min Range: -0.2548

Max Act: 0.2544. Min Act: -0.0001

Data Index: 459701 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2548. Min Act: -0.0001

Data Index: 1090698 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2409. Min Act: -0.0001

Data Index: 470321 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2383. Min Act: -0.0001

Data Index: 1189809 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2398. Min Act: -0.0000

Data Index: 600920 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2280. Min Act: -0.0001

Data Index: 79369 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2109. Min Act: -0.0000

Data Index: 874809 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2471. Min Act: -0.0001

Data Index: 225245 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2299. Min Act: -0.0001

Data Index: 996864 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2399. Min Act: -0.0000

Data Index: 355489 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1009819 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2356. Min Act: -0.0001

Data Index: 370494 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1024960 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2312. Min Act: -0.0001

Data Index: 1079019 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2084. Min Act: -0.0001

Data Index: 17826 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2099. Min Act: -0.0001

Data Index: 17050 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2160. Min Act: -0.0001

Data Index: 755814 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2311. Min Act: -0.0000

Data Index: 311711 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1160124 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.2548. Min Range: -0.2548

Max Act: 0.2115. Min Act: -0.0000

Data Index: 33021 (C4 (Web Text))

Max Activating Token Index: 146