Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3140 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6882. Min Act: -0.0000

Data Index: 49780 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6272. Min Act: -0.0000

Data Index: 477180 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.6291. Min Act: -0.0000

Data Index: 1845305 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1940911 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.5261. Min Act: -0.0000

Data Index: 556856 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4756. Min Act: -0.0000

Data Index: 214446 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4835. Min Act: -0.0000

Data Index: 1468212 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.3899. Min Act: -0.0000

Data Index: 1275227 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4638. Min Act: -0.0000

Data Index: 1172614 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.5377. Min Act: -0.0000

Data Index: 87950 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.5239. Min Act: -0.0000

Data Index: 145335 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1022568 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.3775. Min Act: -0.0000

Data Index: 185081 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4400. Min Act: -0.0000

Data Index: 715071 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.3633. Min Act: -0.0000

Data Index: 574836 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1682322 (The Pile)

Max Activating Token Index: 865

Text #16

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1014896 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.3497. Min Act: -0.0000

Data Index: 949253 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1212537 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 1.6882. Min Range: -1.6882

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1703301 (The Pile)

Max Activating Token Index: 403