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

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

Neuron 935 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: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1517986 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1439096 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1637455 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1625743 (Python Code)

Max Activating Token Index: 744

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1387255 (Python Code)

Max Activating Token Index: 806

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1472488 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1467661 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1504818 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1643192 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1373843 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1586393 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1574746 (Python Code)

Max Activating Token Index: 972

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1632971 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1509785 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1444286 (Python Code)

Max Activating Token Index: 665

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1362891 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1460435 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1425905 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1380712 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1456499 (Python Code)

Max Activating Token Index: 629