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

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

Neuron 3994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2424. Min Act: -0.0000

Data Index: 467209 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1301113 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1251496 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2303. Min Act: -0.0000

Data Index: 193850 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2030. Min Act: -0.0000

Data Index: 716269 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2065. Min Act: -0.0000

Data Index: 491717 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1180650 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1216522 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1897. Min Act: -0.0000

Data Index: 862788 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1953. Min Act: -0.0000

Data Index: 861836 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1878. Min Act: -0.0000

Data Index: 509641 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1169770 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1976. Min Act: -0.0000

Data Index: 930574 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1890. Min Act: -0.0000

Data Index: 771831 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1109784 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1887. Min Act: -0.0000

Data Index: 773890 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1138530 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1754. Min Act: -0.0000

Data Index: 372268 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1816. Min Act: -0.0000

Data Index: 57717 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1183100 (C4 (Web Text))

Max Activating Token Index: 937