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

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

Neuron 4523 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1609270 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1449630 (Python Code)

Max Activating Token Index: 625

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1258579 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1079225 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0736. Min Act: -0.0000

Data Index: 788091 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0735. Min Act: -0.0000

Data Index: 685109 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0734. Min Act: -0.0000

Data Index: 241057 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0733. Min Act: -0.0000

Data Index: 18983 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1619951 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0733. Min Act: -0.0001

Data Index: 577681 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1362101 (Python Code)

Max Activating Token Index: 691

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0705. Min Act: -0.0000

Data Index: 298194 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1169961 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1370641 (Python Code)

Max Activating Token Index: 725

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1365001 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1623892 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1273038 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1539057 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0731. Min Act: -0.0001

Data Index: 159851 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1495392 (Python Code)

Max Activating Token Index: 683