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

Dataset: The Pile

Neuron 413 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1363305 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1275448 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8582. Min Act: 0.0000

Data Index: 1501668 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8987. Min Act: -0.0000

Data Index: 264819 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8084. Min Act: -0.0000

Data Index: 936690 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.6887. Min Act: -0.0000

Data Index: 685234 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8238. Min Act: -0.0000

Data Index: 472197 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8645. Min Act: -0.0000

Data Index: 630492 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7649. Min Act: -0.0000

Data Index: 891687 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1230557 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8157. Min Act: -0.0000

Data Index: 180312 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8063. Min Act: 0.0000

Data Index: 1043702 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7781. Min Act: -0.0000

Data Index: 168100 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1770847 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7480. Min Act: -0.0000

Data Index: 785191 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1495675 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7505. Min Act: -0.0000

Data Index: 358781 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7381. Min Act: -0.0000

Data Index: 58937 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1594766 (The Pile)

Max Activating Token Index: 913

Text #19

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7745. Min Act: -0.0000

Data Index: 310128 (The Pile)

Max Activating Token Index: 646