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

Dataset: The Pile

Neuron 4079 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.0424. Min Range: -10.0424

Max Act: 10.0424. Min Act: -0.0000

Data Index: 1515975 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.7362. Min Act: -0.0000

Data Index: 868233 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.7765. Min Act: -0.0000

Data Index: 1872507 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.6612. Min Act: -0.0000

Data Index: 1588020 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.4544. Min Act: -0.0000

Data Index: 1315382 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.5074. Min Act: -0.0000

Data Index: 1455404 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.2588. Min Act: -0.0000

Data Index: 569690 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.3301. Min Act: -0.0000

Data Index: 1980916 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.2397. Min Act: -0.0000

Data Index: 1896263 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.3734. Min Act: -0.0000

Data Index: 836161 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.5104. Min Act: -0.0000

Data Index: 1647726 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.3146. Min Act: -0.0000

Data Index: 1977528 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.2710. Min Act: -0.0000

Data Index: 607116 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.5008. Min Act: -0.0000

Data Index: 1171608 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 10.0424. Min Range: -10.0424

Max Act: 8.8898. Min Act: -0.0000

Data Index: 753335 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.5068. Min Act: -0.0000

Data Index: 1439752 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 10.0424. Min Range: -10.0424

Max Act: 8.9850. Min Act: -0.0000

Data Index: 1951319 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 10.0424. Min Range: -10.0424

Max Act: 8.8749. Min Act: -0.0000

Data Index: 1453258 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 10.0424. Min Range: -10.0424

Max Act: 8.8933. Min Act: -0.0000

Data Index: 1614905 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 10.0424. Min Range: -10.0424

Max Act: 9.0183. Min Act: -0.0000

Data Index: 1050254 (The Pile)

Max Activating Token Index: 312