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

Dataset: The Pile

Neuron 1638 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1541381 (The Pile)

Max Activating Token Index: 451

Text #1

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1183714 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1374812 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1239857 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.9204. Min Act: -0.0000

Data Index: 127146 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1296486 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8772. Min Act: -0.0000

Data Index: 389173 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.8632. Min Act: -0.0000

Data Index: 815379 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7917. Min Act: -0.0000

Data Index: 255485 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1570430 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7354. Min Act: -0.0000

Data Index: 33510 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1752824 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1989999 (The Pile)

Max Activating Token Index: 858

Text #13

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1507693 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1850131 (The Pile)

Max Activating Token Index: 765

Text #15

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1327024 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7441. Min Act: -0.0000

Data Index: 353975 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7008. Min Act: -0.0000

Data Index: 721242 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1771369 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 0.9641. Min Range: -0.9641

Max Act: 0.7387. Min Act: -0.0000

Data Index: 998737 (The Pile)

Max Activating Token Index: 109