Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 710 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1385. Min Act: -0.0003

Data Index: 1364994 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1520342 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0839. Min Act: -0.0003

Data Index: 1645166 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1580506 (Python Code)

Max Activating Token Index: 268

Text #4

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1591674 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0844. Min Act: -0.0003

Data Index: 1494878 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1483686 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1460330 (Python Code)

Max Activating Token Index: 897

Text #8

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1557684 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0735. Min Act: -0.0003

Data Index: 1393086 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1567160 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1622598 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0702. Min Act: -0.0003

Data Index: 297436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1496556 (Python Code)

Max Activating Token Index: 456

Text #14

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1552303 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1611468 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1385422 (Python Code)

Max Activating Token Index: 153

Text #17

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1622011 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1582147 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1413749 (Python Code)

Max Activating Token Index: 462