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

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

Neuron 2899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1985. Min Act: -0.0000

Data Index: 909317 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.2045. Min Act: -0.0000

Data Index: 331206 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1696. Min Act: -0.0000

Data Index: 783196 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1630. Min Act: -0.0000

Data Index: 682785 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1673. Min Act: -0.0000

Data Index: 112562 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1519. Min Act: -0.0000

Data Index: 941795 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1523. Min Act: -0.0000

Data Index: 329941 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1519. Min Act: -0.0000

Data Index: 423286 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1438. Min Act: -0.0000

Data Index: 926310 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1049876 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1376. Min Act: -0.0000

Data Index: 49119 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1580. Min Act: -0.0000

Data Index: 518401 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1417. Min Act: -0.0000

Data Index: 227396 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1456. Min Act: -0.0000

Data Index: 27857 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1498. Min Act: -0.0000

Data Index: 551831 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1332. Min Act: -0.0000

Data Index: 324808 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1375. Min Act: -0.0000

Data Index: 138070 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1339. Min Act: -0.0000

Data Index: 255164 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1373. Min Act: -0.0000

Data Index: 590190 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.2045. Min Range: -0.2045

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1288170 (C4 (Web Text))

Max Activating Token Index: 398