Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0003

Data Index: 266735 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0514. Min Act: -0.0004

Data Index: 425388 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1126079 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0452. Min Act: -0.0003

Data Index: 528393 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0432. Min Act: -0.0003

Data Index: 690454 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1036293 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0443. Min Act: -0.0003

Data Index: 230525 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0441. Min Act: -0.0003

Data Index: 404580 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0419. Min Act: -0.0003

Data Index: 249841 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1168034 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0432. Min Act: -0.0002

Data Index: 809987 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0425. Min Act: -0.0003

Data Index: 255980 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1299437 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0416. Min Act: -0.0002

Data Index: 918229 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0413. Min Act: -0.0004

Data Index: 1000071 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0408. Min Act: -0.0003

Data Index: 90803 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0405. Min Act: -0.0004

Data Index: 790773 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0389. Min Act: -0.0002

Data Index: 690677 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0402. Min Act: -0.0003

Data Index: 888534 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1248089 (C4 (Web Text))

Max Activating Token Index: 264