Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1682 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5775. Min Range: -3.5775

Max Act: 3.5775. Min Act: -0.0001

Data Index: 1051899 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 3.5775. Min Range: -3.5775

Max Act: 3.1806. Min Act: -0.0001

Data Index: 828806 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 3.5775. Min Range: -3.5775

Max Act: 3.1732. Min Act: -0.0001

Data Index: 1234261 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.5775. Min Range: -3.5775

Max Act: 3.0911. Min Act: -0.0001

Data Index: 675286 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.8100. Min Act: -0.0001

Data Index: 933703 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.8929. Min Act: -0.0001

Data Index: 40653 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.6260. Min Act: -0.0001

Data Index: 1100594 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.5583. Min Act: -0.0001

Data Index: 721612 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.5755. Min Act: -0.0001

Data Index: 811732 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.3156. Min Act: -0.0001

Data Index: 1305359 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.4643. Min Act: -0.0001

Data Index: 353090 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.5062. Min Act: -0.0001

Data Index: 1289244 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.2728. Min Act: -0.0001

Data Index: 896919 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.4938. Min Act: -0.0001

Data Index: 1196148 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.1392. Min Act: -0.0000

Data Index: 793451 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.4389. Min Act: -0.0000

Data Index: 1074492 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 3.5775. Min Range: -3.5775

Max Act: 1.9765. Min Act: -0.0001

Data Index: 1047637 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.2905. Min Act: -0.0001

Data Index: 12667 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.2542. Min Act: -0.0001

Data Index: 1040934 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 3.5775. Min Range: -3.5775

Max Act: 2.1855. Min Act: -0.0001

Data Index: 651660 (C4 (Web Text))

Max Activating Token Index: 864