Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9974. Min Act: -0.0002

Data Index: 1479194 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0002

Data Index: 1589147 (Python Code)

Max Activating Token Index: 436

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0671. Min Act: -0.0002

Data Index: 1380565 (Python Code)

Max Activating Token Index: 140

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1430. Min Act: -0.0002

Data Index: 1512842 (Python Code)

Max Activating Token Index: 474

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9660. Min Act: -0.0002

Data Index: 1510084 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0725. Min Act: -0.0002

Data Index: 1529566 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0737. Min Act: -0.0002

Data Index: 1541964 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0587. Min Act: -0.0002

Data Index: 1605579 (Python Code)

Max Activating Token Index: 537

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8378. Min Act: -0.0002

Data Index: 1586325 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8489. Min Act: -0.0002

Data Index: 1558110 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8941. Min Act: -0.0002

Data Index: 1631496 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0158. Min Act: -0.0002

Data Index: 1479238 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0985. Min Act: -0.0002

Data Index: 1428509 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9425. Min Act: -0.0002

Data Index: 1410864 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9679. Min Act: -0.0002

Data Index: 1451603 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0354. Min Act: -0.0002

Data Index: 1529868 (Python Code)

Max Activating Token Index: 709

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0546. Min Act: -0.0002

Data Index: 1580642 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9705. Min Act: -0.0002

Data Index: 1423713 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9938. Min Act: -0.0002

Data Index: 1458817 (Python Code)

Max Activating Token Index: 856

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9488. Min Act: -0.0002

Data Index: 1637016 (Python Code)

Max Activating Token Index: 880