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

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

Neuron 5629 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1796. Min Act: -0.0001

Data Index: 53052 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1768. Min Act: -0.0001

Data Index: 681717 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1860. Min Act: -0.0001

Data Index: 443500 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1677. Min Act: -0.0001

Data Index: 591642 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1600. Min Act: -0.0001

Data Index: 441569 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1529. Min Act: -0.0001

Data Index: 155679 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1695. Min Act: -0.0002

Data Index: 422406 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1718. Min Act: -0.0001

Data Index: 829993 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1711. Min Act: -0.0001

Data Index: 250338 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1635. Min Act: -0.0002

Data Index: 340871 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1592. Min Act: -0.0001

Data Index: 875161 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1616. Min Act: -0.0001

Data Index: 741511 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1635. Min Act: -0.0001

Data Index: 379314 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1555. Min Act: -0.0001

Data Index: 238071 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1506. Min Act: -0.0001

Data Index: 91676 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1659. Min Act: -0.0001

Data Index: 883696 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1533. Min Act: -0.0001

Data Index: 734899 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1577. Min Act: -0.0001

Data Index: 49084 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1530. Min Act: -0.0001

Data Index: 281956 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1521. Min Act: -0.0001

Data Index: 465020 (C4 (Web Text))

Max Activating Token Index: 562