Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2694 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0000

Data Index: 680060 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1949151 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0274. Min Act: -0.0000

Data Index: 1202976 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0282. Min Act: -0.0000

Data Index: 1856265 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1373309 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1645129 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0281. Min Act: -0.0000

Data Index: 419836 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0261. Min Act: -0.0000

Data Index: 389602 (The Pile)

Max Activating Token Index: 127

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1721963 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0254. Min Act: -0.0000

Data Index: 765911 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1989970 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0285. Min Act: -0.0000

Data Index: 550668 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0254. Min Act: -0.0000

Data Index: 593321 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1726777 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0256. Min Act: -0.0000

Data Index: 878404 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0243. Min Act: -0.0000

Data Index: 1798384 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0249. Min Act: -0.0000

Data Index: 1392518 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0261. Min Act: -0.0000

Data Index: 779976 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1073130 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1860357 (The Pile)

Max Activating Token Index: 219