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

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

Neuron 572 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0001

Data Index: 603196 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0831. Min Act: -0.0001

Data Index: 504564 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0818. Min Act: -0.0001

Data Index: 120259 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0723. Min Act: -0.0000

Data Index: 728966 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0720. Min Act: -0.0001

Data Index: 419841 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0718. Min Act: -0.0001

Data Index: 550790 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0675. Min Act: -0.0000

Data Index: 1279073 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0690. Min Act: -0.0001

Data Index: 387307 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1226313 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0679. Min Act: -0.0001

Data Index: 259847 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1356328 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1334451 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0631. Min Act: -0.0001

Data Index: 28489 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0650. Min Act: -0.0001

Data Index: 500273 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0648. Min Act: -0.0001

Data Index: 320664 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0630. Min Act: -0.0000

Data Index: 677817 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1329614 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1236016 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0633. Min Act: -0.0001

Data Index: 577307 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0617. Min Act: -0.0001

Data Index: 925184 (C4 (Web Text))

Max Activating Token Index: 301