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

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

Neuron 2660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2435. Min Act: -0.0002

Data Index: 1133488 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2044. Min Act: -0.0002

Data Index: 81155 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2019. Min Act: -0.0002

Data Index: 209908 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2081. Min Act: -0.0002

Data Index: 536770 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.2000. Min Act: -0.0002

Data Index: 255066 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1958. Min Act: -0.0002

Data Index: 1359034 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1929. Min Act: -0.0002

Data Index: 966823 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1288292 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1997. Min Act: -0.0002

Data Index: 443290 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1842. Min Act: -0.0002

Data Index: 999659 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1823. Min Act: -0.0002

Data Index: 1083128 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1788. Min Act: -0.0002

Data Index: 558326 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1675. Min Act: -0.0002

Data Index: 309628 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1813. Min Act: -0.0002

Data Index: 1112139 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1735. Min Act: -0.0002

Data Index: 540341 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1776. Min Act: -0.0002

Data Index: 995085 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1712. Min Act: -0.0002

Data Index: 606993 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1759. Min Act: -0.0002

Data Index: 470609 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1664. Min Act: -0.0002

Data Index: 110845 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.2435. Min Range: -0.2435

Max Act: 0.1630. Min Act: -0.0002

Data Index: 612620 (C4 (Web Text))

Max Activating Token Index: 284