Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3354 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0000

Data Index: 811406 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0788. Min Act: -0.0000

Data Index: 512842 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0721. Min Act: -0.0000

Data Index: 962865 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0698. Min Act: -0.0000

Data Index: 561543 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1290272 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0572. Min Act: -0.0000

Data Index: 97443 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0583. Min Act: -0.0000

Data Index: 3469 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0583. Min Act: -0.0000

Data Index: 819725 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0599. Min Act: -0.0000

Data Index: 940903 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0571. Min Act: -0.0000

Data Index: 581307 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0585. Min Act: -0.0000

Data Index: 538977 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0541. Min Act: -0.0000

Data Index: 44710 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1175430 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0556. Min Act: -0.0000

Data Index: 252659 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1237864 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0557. Min Act: -0.0000

Data Index: 1262003 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0554. Min Act: 0.0000

Data Index: 834987 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0506. Min Act: -0.0000

Data Index: 412384 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0543. Min Act: -0.0000

Data Index: 2425 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0518. Min Act: -0.0000

Data Index: 1111887 (C4 (Web Text))

Max Activating Token Index: 1011