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

Dataset: The Pile

Neuron 3311 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: 1.0458. Min Range: -1.0458

Max Act: 1.0458. Min Act: -0.0000

Data Index: 57660 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1707187 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1669933 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0047. Min Act: -0.0000

Data Index: 507673 (The Pile)

Max Activating Token Index: 382

Text #4

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9091. Min Act: -0.0000

Data Index: 291791 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9659. Min Act: -0.0000

Data Index: 713969 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1754888 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1048733 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9678. Min Act: -0.0000

Data Index: 584450 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9236. Min Act: -0.0000

Data Index: 985744 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1788095 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8723. Min Act: -0.0000

Data Index: 406527 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8837. Min Act: -0.0000

Data Index: 766030 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8494. Min Act: -0.0000

Data Index: 601638 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1819867 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1803390 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1237153 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1739446 (The Pile)

Max Activating Token Index: 520

Text #18

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1371704 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1881827 (The Pile)

Max Activating Token Index: 974