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

Dataset: The Pile

Neuron 1287 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4898. Min Range: -3.4898

Max Act: 3.4898. Min Act: -0.0000

Data Index: 209054 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.7366. Min Act: -0.0000

Data Index: 1092653 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.7368. Min Act: -0.0000

Data Index: 197066 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.3675. Min Act: -0.0000

Data Index: 1793610 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.6008. Min Act: -0.0000

Data Index: 239381 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.3006. Min Act: -0.0000

Data Index: 1248817 (The Pile)

Max Activating Token Index: 429

Text #6

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.4298. Min Act: -0.0000

Data Index: 650556 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.6330. Min Act: -0.0000

Data Index: 926571 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.2319. Min Act: -0.0000

Data Index: 376913 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 3.4898. Min Range: -3.4898

Max Act: 1.9641. Min Act: -0.0000

Data Index: 1645108 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.2649. Min Act: -0.0000

Data Index: 703145 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.3693. Min Act: -0.0000

Data Index: 910640 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.3508. Min Act: -0.0000

Data Index: 1952486 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 3.4898. Min Range: -3.4898

Max Act: 1.8844. Min Act: -0.0000

Data Index: 746303 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.2303. Min Act: -0.0000

Data Index: 1895370 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.1061. Min Act: -0.0000

Data Index: 1179649 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.0610. Min Act: -0.0000

Data Index: 641382 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.0206. Min Act: -0.0000

Data Index: 436337 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 3.4898. Min Range: -3.4898

Max Act: 2.4650. Min Act: -0.0000

Data Index: 1630251 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 3.4898. Min Range: -3.4898

Max Act: 1.8620. Min Act: -0.0000

Data Index: 945808 (The Pile)

Max Activating Token Index: 45