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

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

Neuron 406 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3829. Min Act: -0.0000

Data Index: 668463 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3974. Min Act: -0.0000

Data Index: 197010 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3580. Min Act: -0.0000

Data Index: 782526 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.4043. Min Act: -0.0000

Data Index: 106459 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3582. Min Act: -0.0000

Data Index: 211041 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3686. Min Act: -0.0000

Data Index: 674895 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1241765 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3465. Min Act: -0.0000

Data Index: 316915 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3393. Min Act: -0.0000

Data Index: 675574 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3327. Min Act: -0.0000

Data Index: 444011 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3550. Min Act: -0.0000

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3240. Min Act: -0.0000

Data Index: 232610 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3116. Min Act: -0.0000

Data Index: 523603 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3194. Min Act: -0.0000

Data Index: 976757 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3005. Min Act: -0.0000

Data Index: 617789 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1307230 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.2956. Min Act: -0.0000

Data Index: 988516 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.2848. Min Act: -0.0000

Data Index: 234895 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.2896. Min Act: -0.0000

Data Index: 215685 (C4 (Web Text))

Max Activating Token Index: 631