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

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

Neuron 510 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: 0.1817. Min Range: -0.1817

Max Act: 0.1817. Min Act: -0.0000

Data Index: 241512 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1639. Min Act: -0.0000

Data Index: 539328 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1713. Min Act: -0.0000

Data Index: 641521 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1691. Min Act: -0.0000

Data Index: 936224 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1573. Min Act: -0.0000

Data Index: 860453 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1342594 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1625. Min Act: -0.0000

Data Index: 183328 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1060251 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1398. Min Act: -0.0000

Data Index: 369960 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1429. Min Act: -0.0000

Data Index: 351306 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1477. Min Act: -0.0001

Data Index: 343667 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1437. Min Act: -0.0001

Data Index: 374222 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1533. Min Act: -0.0000

Data Index: 112306 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1072400 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1486. Min Act: -0.0000

Data Index: 535143 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1420. Min Act: -0.0000

Data Index: 240930 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1465. Min Act: -0.0000

Data Index: 60574 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1559912 (Python Code)

Max Activating Token Index: 216

Text #18

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1625182 (Python Code)

Max Activating Token Index: 239

Text #19

Max Range: 0.1817. Min Range: -0.1817

Max Act: 0.1311. Min Act: -0.0000

Data Index: 610407 (C4 (Web Text))

Max Activating Token Index: 707