Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1059 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.5010. Min Act: -0.0000

Data Index: 891477 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.4075. Min Act: -0.0000

Data Index: 60299 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1873025 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1491220 (The Pile)

Max Activating Token Index: 704

Text #4

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3589. Min Act: -0.0000

Data Index: 177984 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1608517 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1723479 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1780824 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1502447 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3662. Min Act: -0.0000

Data Index: 578977 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3297. Min Act: -0.0000

Data Index: 777608 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3219. Min Act: -0.0000

Data Index: 269374 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3739. Min Act: -0.0000

Data Index: 578934 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1471603 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3346. Min Act: -0.0000

Data Index: 550840 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3199. Min Act: -0.0000

Data Index: 850873 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1508519 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1144379 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1896426 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.5010. Min Range: -0.5010

Max Act: 0.3247. Min Act: -0.0000

Data Index: 867748 (The Pile)

Max Activating Token Index: 728