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

Dataset: The Pile

Neuron 2440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1259112 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7275. Min Act: -0.0000

Data Index: 131560 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1828598 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1233005 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1030876 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6781. Min Act: -0.0000

Data Index: 817315 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.5178. Min Act: -0.0000

Data Index: 17404 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6388. Min Act: -0.0000

Data Index: 75932 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6312. Min Act: -0.0000

Data Index: 67646 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7935. Min Act: -0.0000

Data Index: 515588 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1294504 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6619. Min Act: -0.0000

Data Index: 550874 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1556637 (The Pile)

Max Activating Token Index: 844

Text #13

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1365538 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6196. Min Act: -0.0000

Data Index: 626036 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1240945 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1024545 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1384945 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1391850 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.9339. Min Range: -0.9339

Max Act: 0.6400. Min Act: -0.0000

Data Index: 388907 (The Pile)

Max Activating Token Index: 747