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

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

Neuron 537 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: 0.2892. Min Range: -0.2892

Max Act: 0.2712. Min Act: -0.0000

Data Index: 433854 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2892. Min Act: -0.0001

Data Index: 322118 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2436. Min Act: -0.0001

Data Index: 686986 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2428. Min Act: -0.0000

Data Index: 454520 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2192. Min Act: -0.0000

Data Index: 921012 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2146. Min Act: -0.0000

Data Index: 78219 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2125. Min Act: -0.0000

Data Index: 914473 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1211854 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2083. Min Act: -0.0000

Data Index: 493537 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1987. Min Act: -0.0001

Data Index: 434899 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1123509 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.2176. Min Act: -0.0001

Data Index: 981133 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1283305 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1989. Min Act: -0.0000

Data Index: 229512 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1249087 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1061556 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1814. Min Act: -0.0000

Data Index: 279049 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1704. Min Act: -0.0000

Data Index: 279913 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1770. Min Act: -0.0000

Data Index: 634472 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.2892. Min Range: -0.2892

Max Act: 0.1743. Min Act: -0.0001

Data Index: 952255 (C4 (Web Text))

Max Activating Token Index: 470