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

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

Neuron 1872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0947. Min Act: -0.0001

Data Index: 94007 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1446. Min Act: -0.0001

Data Index: 879433 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1340. Min Act: -0.0001

Data Index: 262254 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1865. Min Act: -0.0001

Data Index: 154453 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0666. Min Act: -0.0001

Data Index: 482339 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0559. Min Act: -0.0001

Data Index: 1139252 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0123. Min Act: -0.0001

Data Index: 438184 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9295. Min Act: -0.0001

Data Index: 797498 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9159. Min Act: -0.0001

Data Index: 530487 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9066. Min Act: -0.0001

Data Index: 757821 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9046. Min Act: -0.0001

Data Index: 722795 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9045. Min Act: -0.0001

Data Index: 364258 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9317. Min Act: -0.0001

Data Index: 205825 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9160. Min Act: -0.0001

Data Index: 280123 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9422. Min Act: -0.0001

Data Index: 44794 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9102. Min Act: -0.0001

Data Index: 1058204 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9006. Min Act: -0.0001

Data Index: 1100992 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8624. Min Act: -0.0001

Data Index: 829918 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8544. Min Act: -0.0001

Data Index: 21609 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8195. Min Act: -0.0001

Data Index: 36167 (C4 (Web Text))

Max Activating Token Index: 267