Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3417 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1308674 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1638904 (Python Code)

Max Activating Token Index: 695

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0653. Min Act: -0.0001

Data Index: 842876 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0585. Min Act: -0.0001

Data Index: 183956 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0589. Min Act: -0.0000

Data Index: 871569 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0588. Min Act: -0.0001

Data Index: 647953 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0634. Min Act: -0.0001

Data Index: 269114 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1482754 (Python Code)

Max Activating Token Index: 60

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0578. Min Act: -0.0000

Data Index: 905354 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0587. Min Act: -0.0001

Data Index: 938637 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1321473 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0574. Min Act: -0.0000

Data Index: 179061 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0556. Min Act: -0.0001

Data Index: 179787 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1041527 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0573. Min Act: -0.0000

Data Index: 356349 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0549. Min Act: -0.0001

Data Index: 822583 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1085076 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0541. Min Act: -0.0001

Data Index: 473484 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1188833 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1189198 (C4 (Web Text))

Max Activating Token Index: 1002