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

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

Neuron 3594 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: 0.2095. Min Range: -0.2095

Max Act: 0.2095. Min Act: -0.0000

Data Index: 651110 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.2002. Min Act: 0.0000

Data Index: 352257 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1976. Min Act: -0.0000

Data Index: 392646 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1142305 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1112091 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1062658 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1885. Min Act: -0.0000

Data Index: 210838 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1788. Min Act: -0.0001

Data Index: 630510 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1196578 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1760. Min Act: 0.0000

Data Index: 565528 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1769. Min Act: 0.0000

Data Index: 284808 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1183954 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1811. Min Act: 0.0000

Data Index: 591723 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1860. Min Act: -0.0000

Data Index: 250446 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1867. Min Act: 0.0000

Data Index: 585017 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1726. Min Act: -0.0001

Data Index: 804840 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1086444 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1792. Min Act: -0.0001

Data Index: 786556 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1776. Min Act: -0.0000

Data Index: 171744 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.2095. Min Range: -0.2095

Max Act: 0.1754. Min Act: -0.0000

Data Index: 369358 (C4 (Web Text))

Max Activating Token Index: 157