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

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

Neuron 66 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: 1.2503. Min Range: -1.2503

Max Act: 1.2503. Min Act: -0.0001

Data Index: 1315696 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0542. Min Act: -0.0001

Data Index: 125785 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.1156. Min Act: -0.0001

Data Index: 61567 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.1490. Min Act: -0.0001

Data Index: 713860 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.1447. Min Act: -0.0001

Data Index: 450737 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.1364. Min Act: -0.0001

Data Index: 1183709 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.1348. Min Act: -0.0001

Data Index: 1257067 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.1226. Min Act: -0.0001

Data Index: 1235516 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0792. Min Act: -0.0001

Data Index: 462340 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.9993. Min Act: -0.0001

Data Index: 253825 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0834. Min Act: -0.0001

Data Index: 100170 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1256139 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0860. Min Act: -0.0001

Data Index: 355063 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0099. Min Act: -0.0001

Data Index: 838460 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0484. Min Act: -0.0001

Data Index: 19807 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0763. Min Act: -0.0001

Data Index: 873422 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0142. Min Act: -0.0001

Data Index: 497886 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 1.2503. Min Range: -1.2503

Max Act: 0.9670. Min Act: -0.0001

Data Index: 773987 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0017. Min Act: -0.0001

Data Index: 14605 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.2503. Min Range: -1.2503

Max Act: 1.0033. Min Act: -0.0001

Data Index: 12415 (C4 (Web Text))

Max Activating Token Index: 843