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

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

Neuron 5959 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: 0.1864. Min Range: -0.1864

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1364049 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1601108 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1506914 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1374065 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1536862 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1492903 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1587742 (Python Code)

Max Activating Token Index: 588

Text #7

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1529088 (Python Code)

Max Activating Token Index: 575

Text #8

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1511814 (Python Code)

Max Activating Token Index: 223

Text #9

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1589801 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1590296 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1630983 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1649892 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1398257 (Python Code)

Max Activating Token Index: 823

Text #14

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1431276 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1428592 (Python Code)

Max Activating Token Index: 500

Text #16

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1410115 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1506378 (Python Code)

Max Activating Token Index: 962

Text #18

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1526199 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 0.1864. Min Range: -0.1864

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1545011 (Python Code)

Max Activating Token Index: 916