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

Dataset: The Pile

Neuron 110 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.8057. Min Act: -0.0000

Data Index: 317040 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5768. Min Act: -0.0000

Data Index: 197259 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.7238. Min Act: -0.0000

Data Index: 291341 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1375403 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4945. Min Act: -0.0000

Data Index: 589087 (The Pile)

Max Activating Token Index: 544

Text #5

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2319. Min Act: -0.0000

Data Index: 632453 (The Pile)

Max Activating Token Index: 658

Text #6

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3656. Min Act: -0.0000

Data Index: 578277 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3246. Min Act: -0.0000

Data Index: 213344 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1272956 (The Pile)

Max Activating Token Index: 671

Text #9

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2919. Min Act: -0.0000

Data Index: 362973 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1180090 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1805012 (The Pile)

Max Activating Token Index: 320

Text #12

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1386005 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0429. Min Act: -0.0000

Data Index: 1793326 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1100095 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1574665 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0548. Min Act: -0.0000

Data Index: 866127 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1052346 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1459884 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 1.8057. Min Range: -1.8057

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1583296 (The Pile)

Max Activating Token Index: 614