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

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

Neuron 371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2831. Min Act: -0.0001

Data Index: 652881 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0001

Data Index: 568487 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2741. Min Act: -0.0001

Data Index: 825535 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2632. Min Act: -0.0001

Data Index: 996356 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2702. Min Act: -0.0001

Data Index: 276409 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2679. Min Act: -0.0001

Data Index: 1063613 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2573. Min Act: -0.0001

Data Index: 1410940 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2758. Min Act: -0.0001

Data Index: 910824 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2627. Min Act: -0.0001

Data Index: 171121 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2602. Min Act: -0.0001

Data Index: 860205 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2584. Min Act: -0.0001

Data Index: 440725 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2568. Min Act: -0.0001

Data Index: 913752 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2566. Min Act: -0.0001

Data Index: 959817 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2542. Min Act: -0.0000

Data Index: 571533 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1215629 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2587. Min Act: -0.0001

Data Index: 518244 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2378. Min Act: -0.0001

Data Index: 211723 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2420. Min Act: -0.0001

Data Index: 104919 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2540. Min Act: -0.0001

Data Index: 954072 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2469. Min Act: -0.0001

Data Index: 703692 (C4 (Web Text))

Max Activating Token Index: 721