Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 867 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1479. Min Act: -0.0005

Data Index: 54536 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1347. Min Act: -0.0005

Data Index: 665237 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1276. Min Act: -0.0005

Data Index: 1176023 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1181. Min Act: -0.0005

Data Index: 113276 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1178. Min Act: -0.0005

Data Index: 1073341 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1204. Min Act: -0.0005

Data Index: 147587 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1213. Min Act: -0.0005

Data Index: 513505 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1263. Min Act: -0.0005

Data Index: 23156 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1219. Min Act: -0.0005

Data Index: 696509 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1169. Min Act: -0.0005

Data Index: 252904 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1080. Min Act: -0.0005

Data Index: 977663 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1092. Min Act: -0.0005

Data Index: 1092536 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1066. Min Act: -0.0005

Data Index: 176227 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1089. Min Act: -0.0005

Data Index: 857160 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1085. Min Act: -0.0005

Data Index: 641553 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1061. Min Act: -0.0005

Data Index: 1214936 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1060. Min Act: -0.0005

Data Index: 16689 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1078. Min Act: -0.0005

Data Index: 1207760 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1063. Min Act: -0.0005

Data Index: 603918 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1081. Min Act: -0.0005

Data Index: 1107938 (C4 (Web Text))

Max Activating Token Index: 962