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

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

Neuron 987 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1797. Min Act: -0.0001

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1318008 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1564. Min Act: -0.0001

Data Index: 384994 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1009125 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1361. Min Act: -0.0001

Data Index: 659905 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1126. Min Act: -0.0001

Data Index: 682902 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1209. Min Act: -0.0001

Data Index: 42148 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1265. Min Act: -0.0001

Data Index: 464924 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1238. Min Act: -0.0001

Data Index: 270594 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1229. Min Act: -0.0001

Data Index: 744367 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1094. Min Act: -0.0001

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1115. Min Act: -0.0001

Data Index: 523305 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1189. Min Act: -0.0001

Data Index: 406061 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1008917 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1111. Min Act: -0.0001

Data Index: 418697 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1188. Min Act: -0.0001

Data Index: 804843 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1134. Min Act: -0.0001

Data Index: 502655 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1083. Min Act: -0.0001

Data Index: 640535 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1175. Min Act: -0.0001

Data Index: 816520 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.1797. Min Range: -0.1797

Max Act: 0.1125. Min Act: -0.0001

Data Index: 540599 (C4 (Web Text))

Max Activating Token Index: 725