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

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

Neuron 4237 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1268857 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2199. Min Act: -0.0000

Data Index: 883086 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2169. Min Act: -0.0000

Data Index: 919161 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.2102. Min Act: 0.0001

Data Index: 628070 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1946. Min Act: -0.0000

Data Index: 368348 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1879. Min Act: -0.0000

Data Index: 96567 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1828. Min Act: 0.0000

Data Index: 391301 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1927. Min Act: -0.0000

Data Index: 955640 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1737. Min Act: -0.0000

Data Index: 116637 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1787. Min Act: -0.0000

Data Index: 959085 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1022191 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1003692 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1803. Min Act: -0.0000

Data Index: 625650 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1714. Min Act: -0.0000

Data Index: 635396 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1270046 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1128908 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1155869 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1261113 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1070727 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.2258. Min Range: -0.2258

Max Act: 0.1520. Min Act: -0.0000

Data Index: 520223 (C4 (Web Text))

Max Activating Token Index: 212