Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1616284 (Python Code)

Max Activating Token Index: 377

Text #1

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1384707 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1537165 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1389541 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1421081 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1517577 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0541. Min Act: -0.0003

Data Index: 1514569 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1405302 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1435605 (Python Code)

Max Activating Token Index: 280

Text #9

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1459756 (Python Code)

Max Activating Token Index: 901

Text #10

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1415392 (Python Code)

Max Activating Token Index: 435

Text #11

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0504. Min Act: -0.0004

Data Index: 1371162 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1392945 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1433244 (Python Code)

Max Activating Token Index: 859

Text #14

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0479. Min Act: -0.0003

Data Index: 878041 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1418786 (Python Code)

Max Activating Token Index: 328

Text #16

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1439264 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1656082 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1646318 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.0623. Min Range: -0.0623

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1583749 (Python Code)

Max Activating Token Index: 66