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

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

Neuron 4120 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0003

Data Index: 509627 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1082057 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0788. Min Act: -0.0002

Data Index: 939494 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0751. Min Act: -0.0003

Data Index: 250896 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0701. Min Act: -0.0002

Data Index: 805973 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0705. Min Act: -0.0003

Data Index: 788971 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0667. Min Act: -0.0002

Data Index: 868513 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1296048 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0658. Min Act: -0.0003

Data Index: 479485 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1203447 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1210156 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1133670 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0631. Min Act: -0.0003

Data Index: 105494 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0619. Min Act: -0.0002

Data Index: 259017 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0616. Min Act: -0.0003

Data Index: 276309 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0605. Min Act: -0.0003

Data Index: 178680 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1309763 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0617. Min Act: -0.0002

Data Index: 915199 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0605. Min Act: -0.0003

Data Index: 925616 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0594. Min Act: -0.0003

Data Index: 952587 (C4 (Web Text))

Max Activating Token Index: 155