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

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

Neuron 1616 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: 1.2940. Min Range: -1.2940

Max Act: 1.2940. Min Act: -0.0001

Data Index: 812960 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.2386. Min Act: -0.0001

Data Index: 1021983 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0877. Min Act: -0.0001

Data Index: 972947 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0849. Min Act: -0.0001

Data Index: 380445 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0896. Min Act: -0.0001

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.1126. Min Act: -0.0001

Data Index: 754451 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0284. Min Act: -0.0001

Data Index: 243302 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9842. Min Act: -0.0001

Data Index: 1219727 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0415. Min Act: -0.0001

Data Index: 287376 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0236. Min Act: -0.0001

Data Index: 678055 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.2940. Min Range: -1.2940

Max Act: 1.0354. Min Act: -0.0001

Data Index: 576186 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9883. Min Act: -0.0001

Data Index: 941110 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9827. Min Act: -0.0001

Data Index: 279647 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9543. Min Act: -0.0001

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9449. Min Act: -0.0001

Data Index: 777551 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9046. Min Act: -0.0001

Data Index: 446970 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9332. Min Act: -0.0001

Data Index: 1037701 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1137438 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.8981. Min Act: -0.0001

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.2940. Min Range: -1.2940

Max Act: 0.9514. Min Act: -0.0001

Data Index: 1191629 (C4 (Web Text))

Max Activating Token Index: 867