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

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

Neuron 73 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: 0.2296. Min Range: -0.2296

Max Act: 0.2272. Min Act: -0.0000

Data Index: 111007 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2296. Min Act: -0.0000

Data Index: 935711 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2238. Min Act: -0.0001

Data Index: 512409 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2216. Min Act: -0.0001

Data Index: 348732 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1959. Min Act: -0.0001

Data Index: 487143 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2032. Min Act: -0.0001

Data Index: 367656 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2012. Min Act: -0.0001

Data Index: 1074950 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.2051. Min Act: -0.0000

Data Index: 84480 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1223097 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1758. Min Act: -0.0000

Data Index: 623769 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1356195 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1204564 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1746. Min Act: -0.0000

Data Index: 921532 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1185023 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1670. Min Act: -0.0000

Data Index: 595888 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1633. Min Act: -0.0001

Data Index: 76934 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1756. Min Act: -0.0000

Data Index: 717295 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1673. Min Act: -0.0001

Data Index: 844977 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1072216 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.2296. Min Range: -0.2296

Max Act: 0.1781. Min Act: -0.0000

Data Index: 888486 (C4 (Web Text))

Max Activating Token Index: 721