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

Dataset: The Pile

Neuron 1870 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: 1.3031. Min Range: -1.3031

Max Act: 1.3031. Min Act: -0.0000

Data Index: 200413 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.0292. Min Act: -0.0000

Data Index: 426517 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.9800. Min Act: -0.0000

Data Index: 273907 (The Pile)

Max Activating Token Index: 870

Text #3

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.9298. Min Act: -0.0000

Data Index: 1105406 (The Pile)

Max Activating Token Index: 579

Text #4

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.9064. Min Act: -0.0000

Data Index: 296833 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.9202. Min Act: -0.0000

Data Index: 782166 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1226212 (The Pile)

Max Activating Token Index: 875

Text #7

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8672. Min Act: -0.0000

Data Index: 762085 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.9173. Min Act: -0.0000

Data Index: 280870 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.9395. Min Act: -0.0000

Data Index: 263622 (The Pile)

Max Activating Token Index: 868

Text #10

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8073. Min Act: -0.0000

Data Index: 496205 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1748151 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1783086 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8111. Min Act: -0.0000

Data Index: 342351 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8086. Min Act: -0.0000

Data Index: 18771 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8128. Min Act: -0.0000

Data Index: 494608 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8588. Min Act: -0.0000

Data Index: 168788 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.8274. Min Act: -0.0000

Data Index: 211548 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1777762 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 1.3031. Min Range: -1.3031

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1983042 (The Pile)

Max Activating Token Index: 291