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

Dataset: The Pile

Neuron 3443 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: 1.9242. Min Range: -1.9242

Max Act: 1.8744. Min Act: -0.0000

Data Index: 1493 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.9242. Min Act: 0.0000

Data Index: 1540304 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.7070. Min Act: -0.0000

Data Index: 212158 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.7634. Min Act: -0.0000

Data Index: 21700 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5628. Min Act: -0.0000

Data Index: 1259033 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5602. Min Act: -0.0000

Data Index: 507592 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.6569. Min Act: -0.0000

Data Index: 866117 (The Pile)

Max Activating Token Index: 892

Text #7

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.6381. Min Act: -0.0000

Data Index: 763769 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1476870 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.7169. Min Act: -0.0000

Data Index: 1054914 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1536904 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.6006. Min Act: -0.0000

Data Index: 1164639 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1316441 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.6813. Min Act: -0.0000

Data Index: 1174834 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5810. Min Act: -0.0000

Data Index: 844344 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5181. Min Act: -0.0000

Data Index: 821896 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1553984 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1913416 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.4994. Min Act: -0.0000

Data Index: 943523 (The Pile)

Max Activating Token Index: 916

Text #19

Max Range: 1.9242. Min Range: -1.9242

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1540732 (The Pile)

Max Activating Token Index: 685