Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1199808 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1169520 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1361. Min Act: -0.0000

Data Index: 537189 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1599. Min Act: -0.0000

Data Index: 95654 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1479. Min Act: -0.0000

Data Index: 936554 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1136. Min Act: -0.0000

Data Index: 398127 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1353. Min Act: -0.0000

Data Index: 120527 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1278. Min Act: -0.0000

Data Index: 134703 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1177357 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1377. Min Act: -0.0000

Data Index: 597355 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1229. Min Act: -0.0000

Data Index: 194800 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1155. Min Act: -0.0000

Data Index: 373682 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1205. Min Act: -0.0000

Data Index: 782906 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1143. Min Act: -0.0000

Data Index: 791930 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1195. Min Act: -0.0000

Data Index: 522795 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1251. Min Act: -0.0000

Data Index: 212445 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1106. Min Act: -0.0000

Data Index: 790413 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1212594 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1040. Min Act: -0.0000

Data Index: 13233 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1098. Min Act: -0.0000

Data Index: 229022 (C4 (Web Text))

Max Activating Token Index: 226