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

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

Neuron 5039 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: 0.0855. Min Range: -0.0855

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1110774 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0706. Min Act: -0.0001

Data Index: 180742 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0848. Min Act: -0.0001

Data Index: 552064 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1056995 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0805. Min Act: -0.0002

Data Index: 1239246 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0750. Min Act: -0.0001

Data Index: 843312 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0855. Min Act: -0.0001

Data Index: 374623 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0765. Min Act: -0.0001

Data Index: 208461 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1337426 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0667. Min Act: -0.0001

Data Index: 478424 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0803. Min Act: -0.0001

Data Index: 775195 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1355806 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1009194 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0675. Min Act: -0.0001

Data Index: 56027 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0605. Min Act: -0.0001

Data Index: 6916 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0671. Min Act: -0.0001

Data Index: 442806 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0605. Min Act: -0.0001

Data Index: 454320 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0577. Min Act: -0.0001

Data Index: 668594 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1013550 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1554064 (Python Code)

Max Activating Token Index: 276