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

Dataset: The Pile

Neuron 3360 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: 1.0306. Min Range: -1.0306

Max Act: 1.0306. Min Act: -0.0000

Data Index: 480201 (The Pile)

Max Activating Token Index: 540

Text #1

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1511627 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9393. Min Act: -0.0000

Data Index: 511235 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1654010 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1034671 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8931. Min Act: -0.0000

Data Index: 648049 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1225854 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1475377 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 1.0306. Min Range: -1.0306

Max Act: 1.0030. Min Act: -0.0000

Data Index: 873900 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8563. Min Act: -0.0000

Data Index: 579959 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.6546. Min Act: -0.0000

Data Index: 161686 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8939. Min Act: -0.0000

Data Index: 973931 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1976524 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7278. Min Act: -0.0000

Data Index: 842900 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1177233 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1871194 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1364653 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8095. Min Act: -0.0000

Data Index: 736390 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1854908 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7804. Min Act: -0.0000

Data Index: 160138 (The Pile)

Max Activating Token Index: 383