Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 895 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0664. Min Range: -1.0664

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1068231 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.0664. Min Range: -1.0664

Max Act: 1.0202. Min Act: -0.0000

Data Index: 779929 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1327670 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9645. Min Act: 0.0001

Data Index: 159215 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.0664. Min Range: -1.0664

Max Act: 1.0128. Min Act: -0.0000

Data Index: 615688 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9380. Min Act: -0.0000

Data Index: 748738 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1264914 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1100876 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8664. Min Act: -0.0000

Data Index: 507788 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9206. Min Act: -0.0000

Data Index: 927810 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1117554 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8956. Min Act: 0.0003

Data Index: 421013 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1206708 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8855. Min Act: 0.0001

Data Index: 1328728 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8756. Min Act: -0.0000

Data Index: 462078 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8171. Min Act: -0.0000

Data Index: 175341 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1025030 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8521. Min Act: -0.0000

Data Index: 34644 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.8010. Min Act: -0.0000

Data Index: 435994 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.0664. Min Range: -1.0664

Max Act: 0.7856. Min Act: -0.0000

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 791