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

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

Neuron 4614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1069643 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1123. Min Act: -0.0000

Data Index: 680683 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0817. Min Act: -0.0000

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0795. Min Act: -0.0000

Data Index: 671475 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1314870 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1244357 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0719. Min Act: -0.0000

Data Index: 1065384 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0645. Min Act: -0.0000

Data Index: 995218 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0639. Min Act: -0.0000

Data Index: 43978 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0644. Min Act: -0.0000

Data Index: 804598 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0632. Min Act: -0.0000

Data Index: 904819 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0630. Min Act: -0.0000

Data Index: 438879 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0615. Min Act: -0.0000

Data Index: 703792 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0614. Min Act: -0.0000

Data Index: 682211 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0586. Min Act: -0.0000

Data Index: 891460 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0608. Min Act: -0.0000

Data Index: 933552 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0634. Min Act: -0.0000

Data Index: 336440 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1352710 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0608. Min Act: -0.0000

Data Index: 525785 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1295368 (C4 (Web Text))

Max Activating Token Index: 50