Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 611 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1577. Min Act: -0.0001

Data Index: 1570208 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1290. Min Act: -0.0001

Data Index: 1564982 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1333637 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1135. Min Act: -0.0001

Data Index: 1553629 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0905. Min Act: -0.0001

Data Index: 1388870 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1243. Min Act: -0.0001

Data Index: 1413261 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0890. Min Act: -0.0001

Data Index: 1580354 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1385003 (Python Code)

Max Activating Token Index: 669

Text #8

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0874. Min Act: -0.0001

Data Index: 1496607 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0874. Min Act: -0.0001

Data Index: 1647994 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0334. Min Act: -0.0001

Data Index: 1369726 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1565439 (Python Code)

Max Activating Token Index: 515

Text #12

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9655. Min Act: -0.0001

Data Index: 1551968 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9785. Min Act: -0.0001

Data Index: 1476281 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9726. Min Act: -0.0001

Data Index: 1546436 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9670. Min Act: -0.0001

Data Index: 1423686 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9571. Min Act: -0.0001

Data Index: 1648775 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0097. Min Act: -0.0001

Data Index: 743614 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.1577. Min Range: -1.1577

Max Act: 1.0082. Min Act: -0.0001

Data Index: 650609 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 1.1577. Min Range: -1.1577

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1547111 (Python Code)

Max Activating Token Index: 506