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

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

Neuron 2018 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2142. Min Act: -0.0000

Data Index: 956497 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1312230 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1990. Min Act: -0.0000

Data Index: 295647 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1812. Min Act: -0.0000

Data Index: 341346 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1831. Min Act: -0.0000

Data Index: 777120 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1959. Min Act: -0.0000

Data Index: 330855 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1227810 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1072052 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1028827 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1065492 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1753. Min Act: -0.0000

Data Index: 485175 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1806. Min Act: -0.0001

Data Index: 573214 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1723. Min Act: -0.0000

Data Index: 271849 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1755. Min Act: -0.0000

Data Index: 734923 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1613. Min Act: -0.0000

Data Index: 207429 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1630. Min Act: -0.0000

Data Index: 473099 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1733. Min Act: -0.0000

Data Index: 750580 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1672. Min Act: -0.0000

Data Index: 3768 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1645. Min Act: -0.0000

Data Index: 837981 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1530. Min Act: -0.0000

Data Index: 227236 (C4 (Web Text))

Max Activating Token Index: 184