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

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

Neuron 4556 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8345. Min Act: -0.0001

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.9507. Min Act: -0.0001

Data Index: 452917 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8117. Min Act: -0.0001

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.9688. Min Act: -0.0001

Data Index: 174595 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.9310. Min Act: -0.0001

Data Index: 826088 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8617. Min Act: -0.0001

Data Index: 85015 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1167994 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8261. Min Act: -0.0001

Data Index: 56540 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8280. Min Act: -0.0001

Data Index: 804694 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8256. Min Act: -0.0001

Data Index: 979752 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7761. Min Act: -0.0001

Data Index: 276554 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6955. Min Act: -0.0001

Data Index: 855006 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6765. Min Act: -0.0001

Data Index: 309148 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7444. Min Act: -0.0001

Data Index: 863325 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7098. Min Act: -0.0001

Data Index: 32531 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7624. Min Act: -0.0001

Data Index: 569452 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7135. Min Act: -0.0001

Data Index: 504714 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7308. Min Act: -0.0001

Data Index: 285891 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6619. Min Act: -0.0001

Data Index: 517988 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6773. Min Act: -0.0001

Data Index: 734004 (C4 (Web Text))

Max Activating Token Index: 874