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

Dataset: The Pile

Neuron 1362 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.1783. Min Act: -0.0000

Data Index: 420088 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.1270. Min Act: -0.0000

Data Index: 916013 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1428628 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1343295 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1074608 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1918054 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1984267 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.0190. Min Act: -0.0000

Data Index: 388661 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1572258 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.9131. Min Act: -0.0000

Data Index: 86599 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8766. Min Act: -0.0000

Data Index: 861710 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1464890 (The Pile)

Max Activating Token Index: 622

Text #12

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8928. Min Act: -0.0000

Data Index: 925884 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8573. Min Act: -0.0000

Data Index: 101589 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1129729 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8323. Min Act: -0.0000

Data Index: 299103 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1841069 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8736. Min Act: -0.0000

Data Index: 532805 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1403642 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8023. Min Act: -0.0000

Data Index: 787184 (The Pile)

Max Activating Token Index: 738