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

Dataset: The Pile

Neuron 3899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.1830. Min Act: -0.0000

Data Index: 650424 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.2067. Min Act: -0.0000

Data Index: 126600 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.0940. Min Act: -0.0000

Data Index: 54238 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 1.2067. Min Range: -1.2067

Max Act: 1.0339. Min Act: -0.0000

Data Index: 754520 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1614849 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.9659. Min Act: -0.0000

Data Index: 504707 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8915. Min Act: -0.0000

Data Index: 968270 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.9626. Min Act: -0.0000

Data Index: 114647 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8903. Min Act: -0.0000

Data Index: 669804 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1131843 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.9354. Min Act: -0.0000

Data Index: 1315196 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1318979 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.9299. Min Act: -0.0000

Data Index: 379802 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1835658 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1199297 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8115. Min Act: -0.0000

Data Index: 702665 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8689. Min Act: -0.0000

Data Index: 665259 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1649083 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8607. Min Act: -0.0000

Data Index: 638775 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 1.2067. Min Range: -1.2067

Max Act: 0.8845. Min Act: -0.0000

Data Index: 75385 (The Pile)

Max Activating Token Index: 50