Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1819 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1245252 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2052. Min Act: -0.0001

Data Index: 879902 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1070781 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2071. Min Act: -0.0001

Data Index: 236670 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2004. Min Act: -0.0001

Data Index: 859865 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1230903 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1855. Min Act: -0.0001

Data Index: 379832 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1266447 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1924. Min Act: -0.0001

Data Index: 1018007 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1926. Min Act: -0.0001

Data Index: 911619 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1120005 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1886. Min Act: -0.0001

Data Index: 195112 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1859. Min Act: -0.0001

Data Index: 522689 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1806. Min Act: -0.0001

Data Index: 442897 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1730. Min Act: -0.0001

Data Index: 969122 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1934. Min Act: -0.0001

Data Index: 570228 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1004450 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1119039 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1894. Min Act: -0.0001

Data Index: 489198 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1831. Min Act: -0.0001

Data Index: 925891 (C4 (Web Text))

Max Activating Token Index: 957