Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4416 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1135777 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2138. Min Act: -0.0000

Data Index: 692360 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1952. Min Act: -0.0000

Data Index: 791415 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1224081 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1098378 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1849. Min Act: -0.0000

Data Index: 682628 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1241885 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1344803 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1815. Min Act: -0.0000

Data Index: 907408 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1807. Min Act: -0.0000

Data Index: 818722 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1329107 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1597. Min Act: -0.0000

Data Index: 215563 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1587. Min Act: -0.0000

Data Index: 982963 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1704. Min Act: -0.0000

Data Index: 532524 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1673. Min Act: -0.0000

Data Index: 673548 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1642. Min Act: -0.0000

Data Index: 294311 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1563. Min Act: -0.0000

Data Index: 843891 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1773. Min Act: -0.0000

Data Index: 962600 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1725. Min Act: -0.0000

Data Index: 703086 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.2263. Min Range: -0.2263

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1012936 (C4 (Web Text))

Max Activating Token Index: 887