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

Dataset: The Pile

Neuron 2854 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: 1.4632. Min Range: -1.4632

Max Act: 1.4632. Min Act: -0.0000

Data Index: 635276 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1970334 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2802. Min Act: -0.0000

Data Index: 1688585 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3550. Min Act: -0.0000

Data Index: 1635833 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1822. Min Act: 0.0000

Data Index: 1410829 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1112597 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2519. Min Act: -0.0000

Data Index: 1738989 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1694338 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2753. Min Act: -0.0000

Data Index: 88623 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1589700 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1372318 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1380637 (The Pile)

Max Activating Token Index: 173

Text #12

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1528. Min Act: -0.0000

Data Index: 393206 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1184617 (The Pile)

Max Activating Token Index: 217

Text #14

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0737. Min Act: -0.0000

Data Index: 977392 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1877486 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0671. Min Act: -0.0000

Data Index: 681062 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1477810 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1432421 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1942903 (The Pile)

Max Activating Token Index: 744