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

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

Neuron 1557 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0005

Data Index: 1058013 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1646. Min Act: -0.0006

Data Index: 43036 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1759. Min Act: -0.0006

Data Index: 1195761 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1735. Min Act: -0.0006

Data Index: 576352 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1716. Min Act: -0.0006

Data Index: 245255 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1709. Min Act: -0.0006

Data Index: 354922 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1649. Min Act: -0.0006

Data Index: 1046776 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1579. Min Act: -0.0005

Data Index: 1091741 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1517. Min Act: -0.0006

Data Index: 1053216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1626. Min Act: -0.0006

Data Index: 1297961 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1618. Min Act: -0.0006

Data Index: 744559 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1562. Min Act: -0.0006

Data Index: 290824 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1616. Min Act: -0.0006

Data Index: 1016829 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1549. Min Act: -0.0006

Data Index: 1058150 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1607. Min Act: -0.0006

Data Index: 284900 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1599. Min Act: -0.0006

Data Index: 301561 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1703. Min Act: -0.0006

Data Index: 500952 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1574. Min Act: -0.0006

Data Index: 284926 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1572. Min Act: -0.0006

Data Index: 1343430 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1512. Min Act: -0.0006

Data Index: 666258 (C4 (Web Text))

Max Activating Token Index: 9