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

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

Neuron 4213 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1490762 (Python Code)

Max Activating Token Index: 558

Text #1

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1858. Min Act: -0.0000

Data Index: 16715 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1725. Min Act: -0.0000

Data Index: 35437 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1712. Min Act: -0.0000

Data Index: 498987 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1683. Min Act: -0.0000

Data Index: 120932 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1649. Min Act: -0.0000

Data Index: 152288 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1628. Min Act: -0.0000

Data Index: 980224 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.0896. Min Act: -0.0000

Data Index: 81897 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1862. Min Act: -0.0000

Data Index: 94422 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1552. Min Act: -0.0000

Data Index: 829787 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1556. Min Act: -0.0000

Data Index: 868062 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1328666 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1552. Min Act: -0.0000

Data Index: 366224 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1388. Min Act: -0.0000

Data Index: 477617 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1411. Min Act: -0.0000

Data Index: 876128 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1453. Min Act: -0.0000

Data Index: 338925 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1084496 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1363. Min Act: -0.0000

Data Index: 800417 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1313. Min Act: -0.0000

Data Index: 146126 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.2500. Min Range: -0.2500

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1439532 (Python Code)

Max Activating Token Index: 370