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

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

Neuron 4498 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7243. Min Act: -0.0000

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6774. Min Act: -0.0000

Data Index: 612236 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6125. Min Act: -0.0000

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.6152. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5047. Min Act: -0.0000

Data Index: 197125 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5314. Min Act: -0.0000

Data Index: 496797 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1341574 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4865. Min Act: -0.0000

Data Index: 315274 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4434. Min Act: -0.0000

Data Index: 513101 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4362. Min Act: -0.0000

Data Index: 318860 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4890. Min Act: -0.0000

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4448. Min Act: -0.0000

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4569. Min Act: -0.0000

Data Index: 360267 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4509. Min Act: -0.0000

Data Index: 920045 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4229. Min Act: -0.0000

Data Index: 551425 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1137418 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4755. Min Act: -0.0000

Data Index: 230024 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.7243. Min Range: -0.7243

Max Act: 0.4231. Min Act: -0.0000

Data Index: 576318 (C4 (Web Text))

Max Activating Token Index: 922