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

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

Neuron 2983 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: 0.9826. Min Range: -0.9826

Max Act: 0.9826. Min Act: -0.0001

Data Index: 827124 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7974. Min Act: -0.0001

Data Index: 1601997 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7191. Min Act: -0.0001

Data Index: 52239 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7891. Min Act: -0.0001

Data Index: 767812 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7379. Min Act: -0.0001

Data Index: 1626736 (Python Code)

Max Activating Token Index: 195

Text #5

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7086. Min Act: -0.0001

Data Index: 1112241 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7191. Min Act: -0.0001

Data Index: 355955 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1334832 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1298452 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5616. Min Act: -0.0001

Data Index: 79924 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6469. Min Act: -0.0001

Data Index: 894237 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1037215 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6219. Min Act: -0.0001

Data Index: 295109 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6405. Min Act: -0.0001

Data Index: 1436512 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5526. Min Act: -0.0001

Data Index: 148733 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6122. Min Act: -0.0001

Data Index: 862216 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6364. Min Act: -0.0001

Data Index: 753082 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.6154. Min Act: -0.0001

Data Index: 67113 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5648. Min Act: -0.0001

Data Index: 505773 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1610487 (Python Code)

Max Activating Token Index: 39