Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1618 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0000

Data Index: 341152 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1180447 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1295376 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1839. Min Act: -0.0000

Data Index: 155974 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1797. Min Act: -0.0000

Data Index: 575538 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1765. Min Act: -0.0000

Data Index: 243465 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1230069 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1098523 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1646. Min Act: -0.0000

Data Index: 303948 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1038578 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1676. Min Act: -0.0000

Data Index: 290685 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1610. Min Act: -0.0000

Data Index: 101481 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1701. Min Act: -0.0000

Data Index: 947601 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1503. Min Act: -0.0000

Data Index: 192936 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1676. Min Act: -0.0000

Data Index: 201093 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1614. Min Act: -0.0000

Data Index: 85062 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1606. Min Act: -0.0000

Data Index: 706971 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1135138 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1605. Min Act: -0.0000

Data Index: 255655 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1607. Min Act: -0.0000

Data Index: 383162 (C4 (Web Text))

Max Activating Token Index: 548