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

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

Neuron 3800 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2606. Min Act: -0.0000

Data Index: 335488 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2644. Min Act: -0.0000

Data Index: 194820 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2598. Min Act: -0.0000

Data Index: 842938 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2409. Min Act: -0.0000

Data Index: 728081 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1096932 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2217. Min Act: -0.0000

Data Index: 728706 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1302908 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1339622 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2034. Min Act: -0.0000

Data Index: 462662 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1828. Min Act: -0.0000

Data Index: 320137 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1905. Min Act: -0.0000

Data Index: 899977 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2035. Min Act: -0.0000

Data Index: 430605 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1894. Min Act: -0.0000

Data Index: 888012 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1875. Min Act: -0.0000

Data Index: 953201 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1165132 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1187502 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.2070. Min Act: -0.0000

Data Index: 871424 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1320814 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1075004 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.2644. Min Range: -0.2644

Max Act: 0.1828. Min Act: -0.0000

Data Index: 838719 (C4 (Web Text))

Max Activating Token Index: 175