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

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

Neuron 181 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2157. Min Act: -0.0002

Data Index: 714372 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2215. Min Act: -0.0002

Data Index: 694753 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2213. Min Act: -0.0002

Data Index: 942008 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2170. Min Act: -0.0002

Data Index: 392999 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2137. Min Act: -0.0001

Data Index: 894343 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1820. Min Act: -0.0001

Data Index: 147847 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2099. Min Act: -0.0001

Data Index: 644294 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2121. Min Act: -0.0002

Data Index: 658016 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1914. Min Act: -0.0002

Data Index: 1155982 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2008. Min Act: -0.0002

Data Index: 227822 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1942. Min Act: -0.0002

Data Index: 591174 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1572. Min Act: -0.0001

Data Index: 419902 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1974. Min Act: -0.0001

Data Index: 921801 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1907. Min Act: -0.0001

Data Index: 1348741 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1988. Min Act: -0.0001

Data Index: 377340 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1005175 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1892. Min Act: -0.0002

Data Index: 1256027 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1887. Min Act: -0.0001

Data Index: 432626 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1770. Min Act: -0.0001

Data Index: 550954 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1141140 (C4 (Web Text))

Max Activating Token Index: 98