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

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

Neuron 1946 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1164312 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1152657 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2670. Min Act: -0.0001

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2684. Min Act: -0.0000

Data Index: 420274 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2525. Min Act: -0.0001

Data Index: 501760 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2320. Min Act: -0.0001

Data Index: 461009 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2429. Min Act: -0.0000

Data Index: 437893 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2348. Min Act: -0.0000

Data Index: 78555 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2521. Min Act: -0.0001

Data Index: 936594 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2491. Min Act: -0.0000

Data Index: 319711 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2275. Min Act: -0.0000

Data Index: 655695 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2257. Min Act: -0.0000

Data Index: 424278 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2316. Min Act: -0.0000

Data Index: 335077 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2323. Min Act: -0.0000

Data Index: 852588 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2241. Min Act: -0.0000

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2146. Min Act: -0.0001

Data Index: 458907 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1342980 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1030229 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2057. Min Act: -0.0000

Data Index: 590481 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.3036. Min Range: -0.3036

Max Act: 0.2083. Min Act: -0.0000

Data Index: 214213 (C4 (Web Text))

Max Activating Token Index: 556