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

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

Neuron 4936 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2364. Min Act: -0.0001

Data Index: 735668 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1770. Min Act: -0.0001

Data Index: 748004 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1681. Min Act: -0.0001

Data Index: 412308 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1710. Min Act: -0.0001

Data Index: 247147 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1799. Min Act: -0.0001

Data Index: 431228 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1702. Min Act: -0.0001

Data Index: 297373 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1068555 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1330624 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1589. Min Act: -0.0001

Data Index: 169579 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1435. Min Act: -0.0001

Data Index: 857745 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1538. Min Act: -0.0001

Data Index: 213875 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1441. Min Act: -0.0001

Data Index: 439113 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1568. Min Act: -0.0001

Data Index: 150967 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1103943 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1575. Min Act: -0.0001

Data Index: 801262 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1420. Min Act: -0.0001

Data Index: 64801 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1498. Min Act: -0.0001

Data Index: 745541 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1358254 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1290634 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1477. Min Act: -0.0001

Data Index: 989351 (C4 (Web Text))

Max Activating Token Index: 612