Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1249 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0003

Data Index: 537639 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1371. Min Act: -0.0003

Data Index: 1253446 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1383. Min Act: -0.0003

Data Index: 140018 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1322. Min Act: -0.0003

Data Index: 721053 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1253. Min Act: -0.0003

Data Index: 59462 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1190. Min Act: -0.0003

Data Index: 939014 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1281. Min Act: -0.0003

Data Index: 704155 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1242. Min Act: -0.0003

Data Index: 1082094 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1225. Min Act: -0.0003

Data Index: 296526 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1064730 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0991. Min Act: -0.0003

Data Index: 679741 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1215. Min Act: -0.0003

Data Index: 999861 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1231. Min Act: -0.0003

Data Index: 46634 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1131. Min Act: -0.0003

Data Index: 912700 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1197. Min Act: -0.0003

Data Index: 1185296 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1075. Min Act: -0.0003

Data Index: 751539 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1035. Min Act: -0.0003

Data Index: 789310 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1054. Min Act: -0.0003

Data Index: 779805 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0925. Min Act: -0.0003

Data Index: 1119097 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1006. Min Act: -0.0003

Data Index: 413694 (C4 (Web Text))

Max Activating Token Index: 436