Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1018 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0003

Data Index: 674014 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1278204 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0698. Min Act: -0.0003

Data Index: 39539 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0767. Min Act: -0.0003

Data Index: 259762 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0669. Min Act: -0.0003

Data Index: 170196 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0630. Min Act: -0.0003

Data Index: 143736 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0632. Min Act: -0.0003

Data Index: 984851 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0599. Min Act: -0.0003

Data Index: 460518 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0659. Min Act: -0.0003

Data Index: 74996 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0651. Min Act: -0.0003

Data Index: 337069 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0651. Min Act: -0.0003

Data Index: 188141 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0648. Min Act: -0.0003

Data Index: 240436 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1013493 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0580. Min Act: -0.0003

Data Index: 14787 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0541. Min Act: -0.0003

Data Index: 583425 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1141881 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0633. Min Act: -0.0003

Data Index: 869382 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1126459 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1179158 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1320778 (C4 (Web Text))

Max Activating Token Index: 903