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

Dataset: The Pile

Neuron 2849 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: 1.3570. Min Range: -1.3570

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1158371 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1960238 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1787528 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1962. Min Act: -0.0000

Data Index: 700366 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.3245. Min Act: -0.0000

Data Index: 398398 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1436. Min Act: -0.0000

Data Index: 212281 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9611. Min Act: -0.0000

Data Index: 522167 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0466. Min Act: -0.0000

Data Index: 729050 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1996657 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.1073. Min Act: -0.0000

Data Index: 1726260 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1278599 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1154440 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1140589 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0807. Min Act: -0.0000

Data Index: 501939 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9000. Min Act: -0.0000

Data Index: 762420 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1764628 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1938429 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 1.3570. Min Range: -1.3570

Max Act: 1.0320. Min Act: -0.0000

Data Index: 564761 (The Pile)

Max Activating Token Index: 707

Text #19

Max Range: 1.3570. Min Range: -1.3570

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1029103 (The Pile)

Max Activating Token Index: 709