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

Dataset: The Pile

Neuron 254 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: 1.5813. Min Range: -1.5813

Max Act: 1.5813. Min Act: -0.0000

Data Index: 1904222 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.4104. Min Act: -0.0000

Data Index: 315308 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.4463. Min Act: -0.0000

Data Index: 243832 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.5115. Min Act: -0.0000

Data Index: 1108718 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1881934 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.3823. Min Act: -0.0000

Data Index: 552040 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.3183. Min Act: -0.0000

Data Index: 465057 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1133797 (The Pile)

Max Activating Token Index: 276

Text #8

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2727. Min Act: -0.0000

Data Index: 549926 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1006961 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2473. Min Act: 0.0000

Data Index: 1746897 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.3222. Min Act: -0.0000

Data Index: 944421 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1124273 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2726. Min Act: -0.0000

Data Index: 699268 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2666. Min Act: 0.0000

Data Index: 347837 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1510424 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1733. Min Act: -0.0000

Data Index: 845614 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1804639 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.1500. Min Act: -0.0000

Data Index: 128104 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 1.5813. Min Range: -1.5813

Max Act: 1.0908. Min Act: -0.0000

Data Index: 498128 (The Pile)

Max Activating Token Index: 705