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

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

Neuron 3518 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.4890. Min Act: -0.0000

Data Index: 259202 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.5308. Min Act: -0.0000

Data Index: 865347 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.3144. Min Act: -0.0000

Data Index: 987164 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.3128. Min Act: -0.0000

Data Index: 193597 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.2604. Min Act: -0.0000

Data Index: 350155 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1198895 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1115500 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.9905. Min Act: -0.0000

Data Index: 204171 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.9321. Min Act: -0.0000

Data Index: 510664 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1197003 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8782. Min Act: -0.0000

Data Index: 212559 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8765. Min Act: -0.0000

Data Index: 247865 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8935. Min Act: -0.0000

Data Index: 347370 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.9109. Min Act: -0.0000

Data Index: 943078 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8995. Min Act: -0.0000

Data Index: 143828 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8326. Min Act: -0.0000

Data Index: 141034 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8838. Min Act: -0.0000

Data Index: 929891 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8441. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8586. Min Act: -0.0000

Data Index: 415609 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.5308. Min Range: -1.5308

Max Act: 0.8361. Min Act: -0.0000

Data Index: 418599 (C4 (Web Text))

Max Activating Token Index: 486