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

Dataset: The Pile

Neuron 3063 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6642. Min Act: -0.0000

Data Index: 397380 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6502. Min Act: -0.0000

Data Index: 1750619 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1274069 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5755. Min Act: -0.0000

Data Index: 815987 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5855. Min Act: -0.0000

Data Index: 705645 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1377014 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5362. Min Act: -0.0000

Data Index: 327383 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5142. Min Act: -0.0000

Data Index: 837786 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4966. Min Act: -0.0000

Data Index: 922718 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5402. Min Act: -0.0000

Data Index: 58598 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1241900 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1425542 (The Pile)

Max Activating Token Index: 101

Text #12

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4914. Min Act: -0.0000

Data Index: 457490 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1756185 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4953. Min Act: 0.0000

Data Index: 828954 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4634. Min Act: -0.0000

Data Index: 971388 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1984030 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4890. Min Act: -0.0000

Data Index: 262508 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4780. Min Act: -0.0000

Data Index: 80231 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1410197 (The Pile)

Max Activating Token Index: 566