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

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

Neuron 2670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1281268 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1243471 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1464. Min Act: -0.0001

Data Index: 566431 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1442. Min Act: -0.0001

Data Index: 240660 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1318. Min Act: -0.0001

Data Index: 623345 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1308. Min Act: -0.0001

Data Index: 79772 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1375. Min Act: -0.0001

Data Index: 428762 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1272. Min Act: -0.0001

Data Index: 264279 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1180. Min Act: -0.0001

Data Index: 576012 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1248. Min Act: -0.0001

Data Index: 627398 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1241. Min Act: -0.0001

Data Index: 447836 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1284. Min Act: -0.0001

Data Index: 209049 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1268. Min Act: -0.0001

Data Index: 966109 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1114. Min Act: -0.0001

Data Index: 233475 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1130178 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1216. Min Act: -0.0001

Data Index: 677106 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1209. Min Act: -0.0001

Data Index: 665595 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1204. Min Act: -0.0001

Data Index: 828541 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1321957 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.1697. Min Range: -0.1697

Max Act: 0.1089. Min Act: -0.0001

Data Index: 296369 (C4 (Web Text))

Max Activating Token Index: 823