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

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

Neuron 2812 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2024. Min Act: -0.0001

Data Index: 927017 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1095607 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2160. Min Act: -0.0000

Data Index: 695816 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1325616 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1897. Min Act: -0.0000

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1112255 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2260. Min Act: -0.0000

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1960. Min Act: -0.0001

Data Index: 1150451 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1307542 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1792. Min Act: -0.0001

Data Index: 546354 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1748. Min Act: -0.0001

Data Index: 148955 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1673. Min Act: -0.0000

Data Index: 897180 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1766. Min Act: -0.0000

Data Index: 906362 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1879. Min Act: -0.0000

Data Index: 980034 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.2021. Min Act: -0.0000

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1332308 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1689. Min Act: -0.0000

Data Index: 708557 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1266606 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.2299. Min Range: -0.2299

Max Act: 0.1869. Min Act: -0.0000

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 846