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

Dataset: The Pile

Neuron 428 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: 1.0306. Min Range: -1.0306

Max Act: 1.0306. Min Act: -0.0000

Data Index: 497798 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1339982 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7315. Min Act: -0.0000

Data Index: 613094 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1879597 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1258933 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1862006 (The Pile)

Max Activating Token Index: 981

Text #6

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1270127 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6897. Min Act: -0.0000

Data Index: 626238 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7295. Min Act: -0.0000

Data Index: 945433 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7483. Min Act: -0.0000

Data Index: 406467 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6757. Min Act: -0.0000

Data Index: 746318 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1423484 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1333271 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7595. Min Act: -0.0000

Data Index: 321196 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6982. Min Act: -0.0000

Data Index: 975957 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6799. Min Act: -0.0000

Data Index: 255442 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6773. Min Act: -0.0000

Data Index: 162518 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1475315 (The Pile)

Max Activating Token Index: 435

Text #18

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1168598 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1241108 (The Pile)

Max Activating Token Index: 132