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

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

Neuron 2418 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1126345 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0702. Min Act: -0.0001

Data Index: 428114 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0700. Min Act: -0.0001

Data Index: 397687 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0691. Min Act: -0.0001

Data Index: 37281 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0664. Min Act: -0.0001

Data Index: 468696 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0647. Min Act: -0.0001

Data Index: 757975 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1190497 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0610. Min Act: -0.0001

Data Index: 848903 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0602. Min Act: -0.0001

Data Index: 381627 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1211079 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1298804 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0594. Min Act: -0.0000

Data Index: 733951 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0640. Min Act: -0.0001

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1268565 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0581. Min Act: -0.0001

Data Index: 238073 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0559. Min Act: -0.0000

Data Index: 352514 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0561. Min Act: -0.0001

Data Index: 2091 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0536. Min Act: -0.0001

Data Index: 969683 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1071520 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1130874 (C4 (Web Text))

Max Activating Token Index: 601