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

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

Neuron 32 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0001

Data Index: 290185 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0599. Min Act: -0.0001

Data Index: 354201 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1110070 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0553. Min Act: -0.0001

Data Index: 986666 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0529. Min Act: -0.0001

Data Index: 73769 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0563. Min Act: -0.0001

Data Index: 998509 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1300359 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1209716 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0529. Min Act: -0.0001

Data Index: 298526 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1351172 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0496. Min Act: -0.0001

Data Index: 135604 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1286215 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1088399 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0511. Min Act: -0.0001

Data Index: 48919 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1067453 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0533. Min Act: -0.0001

Data Index: 751148 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0486. Min Act: -0.0001

Data Index: 863898 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0448. Min Act: -0.0001

Data Index: 699060 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0478. Min Act: -0.0001

Data Index: 651508 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1002893 (C4 (Web Text))

Max Activating Token Index: 673