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

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

Neuron 1190 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0002

Data Index: 879454 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1175911 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0567. Min Act: -0.0002

Data Index: 649064 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0528. Min Act: -0.0002

Data Index: 177663 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0492. Min Act: -0.0002

Data Index: 61822 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0453. Min Act: -0.0002

Data Index: 646846 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0451. Min Act: -0.0002

Data Index: 702012 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0442. Min Act: -0.0002

Data Index: 806261 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0447. Min Act: -0.0002

Data Index: 652483 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0444. Min Act: -0.0002

Data Index: 176810 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0435. Min Act: -0.0002

Data Index: 114954 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0428. Min Act: -0.0002

Data Index: 335932 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0417. Min Act: -0.0002

Data Index: 121434 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0392. Min Act: -0.0002

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0404. Min Act: -0.0002

Data Index: 981662 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1168787 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0369. Min Act: -0.0002

Data Index: 595455 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0363. Min Act: -0.0002

Data Index: 382972 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0369. Min Act: -0.0002

Data Index: 432331 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1068979 (C4 (Web Text))

Max Activating Token Index: 28