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

Dataset: The Pile

Neuron 3137 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1993552 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2311. Min Act: -0.0000

Data Index: 936668 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2427. Min Act: -0.0000

Data Index: 133852 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1748804 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1402037 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1018149 (The Pile)

Max Activating Token Index: 1015

Text #6

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2183. Min Act: -0.0000

Data Index: 395579 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2197. Min Act: -0.0000

Data Index: 609447 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2018. Min Act: -0.0000

Data Index: 561354 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1635592 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2011. Min Act: -0.0000

Data Index: 91492 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1901242 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1903. Min Act: -0.0000

Data Index: 538091 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1744. Min Act: -0.0000

Data Index: 934701 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1296201 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1886. Min Act: -0.0000

Data Index: 363295 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1049510 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1826. Min Act: -0.0000

Data Index: 738939 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1692. Min Act: -0.0000

Data Index: 626203 (The Pile)

Max Activating Token Index: 254

Text #19

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1007490 (The Pile)

Max Activating Token Index: 622