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

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

Neuron 3616 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1079884 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.8700. Min Act: -0.0000

Data Index: 514976 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.8030. Min Act: -0.0000

Data Index: 658603 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.6454. Min Act: -0.0000

Data Index: 655706 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.6876. Min Act: -0.0001

Data Index: 815697 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.5868. Min Act: -0.0001

Data Index: 121421 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.5464. Min Act: -0.0001

Data Index: 97881 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.5402. Min Act: -0.0001

Data Index: 133188 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.4730. Min Act: -0.0000

Data Index: 926273 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1141685 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.4076. Min Act: -0.0001

Data Index: 890450 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.4001. Min Act: -0.0000

Data Index: 161362 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3933. Min Act: -0.0000

Data Index: 300377 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.4292. Min Act: -0.0000

Data Index: 978960 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3635. Min Act: -0.0000

Data Index: 574668 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3729. Min Act: -0.0001

Data Index: 288155 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3269. Min Act: -0.0001

Data Index: 610369 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3433. Min Act: -0.0000

Data Index: 448551 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3442. Min Act: -0.0000

Data Index: 103838 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.9759. Min Range: -0.9759

Max Act: 0.3245. Min Act: -0.0001

Data Index: 381951 (C4 (Web Text))

Max Activating Token Index: 716