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

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

Neuron 48 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0001

Data Index: 278339 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0787. Min Act: -0.0001

Data Index: 972119 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0770. Min Act: -0.0001

Data Index: 172677 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0680. Min Act: -0.0001

Data Index: 719366 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0786. Min Act: -0.0001

Data Index: 350059 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0637. Min Act: -0.0001

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1112158 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0641. Min Act: -0.0001

Data Index: 680686 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0643. Min Act: -0.0001

Data Index: 507493 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0690. Min Act: -0.0001

Data Index: 775746 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0620. Min Act: -0.0001

Data Index: 1190733 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0585. Min Act: -0.0001

Data Index: 606691 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1468629 (Python Code)

Max Activating Token Index: 280

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0602. Min Act: -0.0001

Data Index: 601638 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0589. Min Act: -0.0001

Data Index: 263157 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1298495 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1412905 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0584. Min Act: -0.0001

Data Index: 908519 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0597. Min Act: -0.0001

Data Index: 224637 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0598. Min Act: -0.0001

Data Index: 545380 (C4 (Web Text))

Max Activating Token Index: 731