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

Dataset: The Pile

Neuron 1588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1897772 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.7821. Min Act: -0.0000

Data Index: 296512 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1002841 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1049265 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1925170 (The Pile)

Max Activating Token Index: 546

Text #5

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1739304 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6335. Min Act: -0.0000

Data Index: 142302 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1165369 (The Pile)

Max Activating Token Index: 635

Text #8

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5926. Min Act: -0.0000

Data Index: 959605 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1565913 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1646690 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5582. Min Act: -0.0000

Data Index: 448603 (The Pile)

Max Activating Token Index: 984

Text #12

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1596624 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1947226 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1075861 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1059751 (The Pile)

Max Activating Token Index: 611

Text #16

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6002. Min Act: -0.0000

Data Index: 218802 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1509489 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5480. Min Act: -0.0000

Data Index: 691836 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5756. Min Act: -0.0000

Data Index: 249330 (The Pile)

Max Activating Token Index: 112