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

Dataset: The Pile

Neuron 5011 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.9153. Min Act: -0.0000

Data Index: 806446 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.7287. Min Act: -0.0000

Data Index: 1389131 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 6.0609. Min Range: -6.0609

Max Act: 6.0609. Min Act: -0.0000

Data Index: 1497514 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.8245. Min Act: -0.0000

Data Index: 976798 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.6896. Min Act: -0.0000

Data Index: 922350 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.5486. Min Act: -0.0000

Data Index: 1188523 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.5229. Min Act: -0.0000

Data Index: 1194224 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.6182. Min Act: -0.0000

Data Index: 537820 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.5734. Min Act: -0.0000

Data Index: 1670943 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.1663. Min Act: -0.0000

Data Index: 1078048 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.3603. Min Act: -0.0000

Data Index: 251765 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 6.0609. Min Range: -6.0609

Max Act: 4.9744. Min Act: -0.0000

Data Index: 1168442 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.1031. Min Act: -0.0000

Data Index: 495825 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.3015. Min Act: -0.0000

Data Index: 750585 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 6.0609. Min Range: -6.0609

Max Act: 4.8372. Min Act: -0.0000

Data Index: 235898 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.1914. Min Act: -0.0000

Data Index: 853633 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 6.0609. Min Range: -6.0609

Max Act: 5.1397. Min Act: -0.0000

Data Index: 344004 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 6.0609. Min Range: -6.0609

Max Act: 4.9634. Min Act: -0.0000

Data Index: 419497 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 6.0609. Min Range: -6.0609

Max Act: 4.8128. Min Act: -0.0000

Data Index: 1138733 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 6.0609. Min Range: -6.0609

Max Act: 4.7429. Min Act: -0.0000

Data Index: 1241852 (The Pile)

Max Activating Token Index: 448