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

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

Neuron 5141 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0000

Data Index: 913018 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1342042 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1335934 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1493. Min Act: -0.0000

Data Index: 913876 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1028948 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1355. Min Act: -0.0000

Data Index: 697355 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1309. Min Act: -0.0000

Data Index: 862233 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1356598 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1399. Min Act: -0.0000

Data Index: 769824 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1343. Min Act: -0.0000

Data Index: 635660 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1361. Min Act: -0.0000

Data Index: 604550 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1294. Min Act: -0.0000

Data Index: 687774 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1396. Min Act: -0.0000

Data Index: 714276 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1058330 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1156. Min Act: -0.0000

Data Index: 297804 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1190. Min Act: -0.0000

Data Index: 677881 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1343691 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1229. Min Act: -0.0000

Data Index: 469749 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1258653 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1239. Min Act: -0.0000

Data Index: 530101 (C4 (Web Text))

Max Activating Token Index: 487