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

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

Neuron 4003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2424. Min Act: -0.0001

Data Index: 514101 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1438792 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1913. Min Act: -0.0001

Data Index: 423306 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1395855 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.2019. Min Act: -0.0001

Data Index: 61268 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1226891 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1056747 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1105492 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1619043 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1141059 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1559. Min Act: -0.0001

Data Index: 978242 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1611. Min Act: -0.0001

Data Index: 545913 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1649. Min Act: -0.0001

Data Index: 594688 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1697. Min Act: -0.0001

Data Index: 722503 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1570. Min Act: -0.0001

Data Index: 507218 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1709. Min Act: -0.0001

Data Index: 552950 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1683. Min Act: -0.0001

Data Index: 370396 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1302657 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1657. Min Act: -0.0001

Data Index: 451104 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.2424. Min Range: -0.2424

Max Act: 0.1605. Min Act: -0.0001

Data Index: 1412718 (Python Code)

Max Activating Token Index: 533