Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1207 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.7496. Min Act: -0.0001

Data Index: 991568 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.5819. Min Act: -0.0001

Data Index: 776576 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.4874. Min Act: -0.0001

Data Index: 626371 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.4105. Min Act: -0.0001

Data Index: 1277564 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.3757. Min Act: -0.0001

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.3348. Min Act: -0.0001

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.0418. Min Act: -0.0001

Data Index: 1253926 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.8423. Min Act: -0.0001

Data Index: 847637 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.1798. Min Act: -0.0001

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.7928. Min Act: -0.0001

Data Index: 344568 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 7.7496. Min Range: -7.7496

Max Act: 7.1163. Min Act: -0.0001

Data Index: 362908 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.5648. Min Act: -0.0001

Data Index: 1108884 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.8971. Min Act: -0.0001

Data Index: 927942 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.6983. Min Act: -0.0001

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.6538. Min Act: -0.0001

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.8287. Min Act: -0.0001

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.8111. Min Act: -0.0001

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.8265. Min Act: -0.0001

Data Index: 202415 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.4372. Min Act: -0.0001

Data Index: 952237 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 7.7496. Min Range: -7.7496

Max Act: 6.3907. Min Act: -0.0001

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 486