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

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

Neuron 3190 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: 1.3376. Min Range: -1.3376

Max Act: 1.1798. Min Act: -0.0001

Data Index: 1343485 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.3006. Min Act: -0.0001

Data Index: 1219588 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.2624. Min Act: -0.0001

Data Index: 830781 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.3376. Min Act: -0.0001

Data Index: 808520 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1611. Min Act: -0.0001

Data Index: 904069 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.2346. Min Act: -0.0001

Data Index: 479975 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1821. Min Act: -0.0001

Data Index: 1148164 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1172. Min Act: -0.0001

Data Index: 1281541 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0811. Min Act: -0.0001

Data Index: 633973 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1614. Min Act: -0.0001

Data Index: 1069624 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1132. Min Act: -0.0001

Data Index: 258692 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1044. Min Act: -0.0001

Data Index: 653598 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1093. Min Act: -0.0001

Data Index: 935136 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0740. Min Act: -0.0001

Data Index: 543733 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0946. Min Act: -0.0001

Data Index: 41906 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1569. Min Act: -0.0001

Data Index: 596370 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1043. Min Act: -0.0001

Data Index: 449882 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0712. Min Act: -0.0001

Data Index: 988224 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.1202. Min Act: -0.0001

Data Index: 441377 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.3376. Min Range: -1.3376

Max Act: 1.0561. Min Act: -0.0001

Data Index: 643103 (C4 (Web Text))

Max Activating Token Index: 629