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

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

Neuron 4751 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2742. Min Act: -0.0001

Data Index: 230603 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2606. Min Act: -0.0001

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2680. Min Act: -0.0001

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2459. Min Act: -0.0001

Data Index: 195667 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2388. Min Act: -0.0001

Data Index: 911814 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2287. Min Act: -0.0001

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2217. Min Act: -0.0001

Data Index: 446745 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2363. Min Act: -0.0001

Data Index: 1121037 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2100. Min Act: -0.0001

Data Index: 523572 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2216. Min Act: -0.0001

Data Index: 1236272 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2364. Min Act: -0.0001

Data Index: 885113 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2093. Min Act: -0.0001

Data Index: 197295 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.1971. Min Act: -0.0001

Data Index: 673028 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2120. Min Act: -0.0001

Data Index: 513093 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1045146 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2109. Min Act: -0.0001

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2043. Min Act: -0.0001

Data Index: 53401 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2013. Min Act: -0.0001

Data Index: 648110 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.2742. Min Range: -0.2742

Max Act: 0.2005. Min Act: -0.0001

Data Index: 92103 (C4 (Web Text))

Max Activating Token Index: 602