Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 777 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1120750 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0681. Min Act: -0.0003

Data Index: 382348 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0549. Min Act: -0.0003

Data Index: 116092 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0613. Min Act: -0.0003

Data Index: 67139 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0645. Min Act: -0.0003

Data Index: 798931 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0659. Min Act: -0.0003

Data Index: 599218 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0692. Min Act: -0.0003

Data Index: 91388 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1188411 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0636. Min Act: -0.0003

Data Index: 796725 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0592. Min Act: -0.0003

Data Index: 601621 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0631. Min Act: -0.0003

Data Index: 944492 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0535. Min Act: -0.0003

Data Index: 840313 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0573. Min Act: -0.0003

Data Index: 337499 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0496. Min Act: -0.0003

Data Index: 214793 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0604. Min Act: -0.0003

Data Index: 191800 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1193008 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1133200 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0555. Min Act: -0.0003

Data Index: 836879 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0586. Min Act: -0.0003

Data Index: 32854 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1306981 (C4 (Web Text))

Max Activating Token Index: 816