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

Dataset: The Pile

Neuron 4593 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: 0.8686. Min Range: -0.8686

Max Act: 0.8686. Min Act: -0.0000

Data Index: 21505 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8582. Min Act: -0.0000

Data Index: 786706 (The Pile)

Max Activating Token Index: 158

Text #2

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8634. Min Act: -0.0000

Data Index: 406001 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1504674 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7939. Min Act: -0.0000

Data Index: 921506 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1073604 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7808. Min Act: -0.0000

Data Index: 625510 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7674. Min Act: -0.0000

Data Index: 884503 (The Pile)

Max Activating Token Index: 129

Text #8

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7429. Min Act: -0.0000

Data Index: 725262 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1776379 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1261614 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7191. Min Act: -0.0000

Data Index: 411940 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1085054 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7639. Min Act: -0.0000

Data Index: 979753 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1405384 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6488. Min Act: -0.0000

Data Index: 600464 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7509. Min Act: -0.0000

Data Index: 325347 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1834836 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1426594 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6834. Min Act: -0.0000

Data Index: 899656 (The Pile)

Max Activating Token Index: 875