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

Dataset: The Pile

Neuron 4323 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: 0.9742. Min Range: -0.9742

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1769301 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.8802. Min Act: -0.0000

Data Index: 814374 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1656131 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1410651 (The Pile)

Max Activating Token Index: 449

Text #4

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1883819 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6738. Min Act: -0.0000

Data Index: 591954 (The Pile)

Max Activating Token Index: 375

Text #6

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1194070 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6818. Min Act: -0.0000

Data Index: 369702 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1324359 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1494695 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6452. Min Act: -0.0000

Data Index: 34953 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1982271 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1972015 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1107204 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1486832 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1569798 (The Pile)

Max Activating Token Index: 519

Text #16

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1320051 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1604112 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1430649 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1739253 (The Pile)

Max Activating Token Index: 114