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

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

Neuron 198 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2427. Min Act: -0.0001

Data Index: 1336321 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2688. Min Act: -0.0000

Data Index: 967274 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2348. Min Act: -0.0000

Data Index: 96777 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1062385 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1973. Min Act: -0.0001

Data Index: 1111556 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1191779 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2038. Min Act: -0.0001

Data Index: 74132 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1874. Min Act: -0.0001

Data Index: 875286 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2056. Min Act: -0.0001

Data Index: 995127 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1975. Min Act: -0.0000

Data Index: 953585 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1922. Min Act: -0.0001

Data Index: 208608 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1921. Min Act: -0.0001

Data Index: 256390 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.2009. Min Act: -0.0001

Data Index: 438617 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1983. Min Act: -0.0001

Data Index: 750649 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1877. Min Act: -0.0001

Data Index: 228897 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1119609 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1796. Min Act: -0.0001

Data Index: 837585 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1924. Min Act: -0.0001

Data Index: 556476 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1193744 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.2688. Min Range: -0.2688

Max Act: 0.1833. Min Act: -0.0001

Data Index: 946052 (C4 (Web Text))

Max Activating Token Index: 125