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

Dataset: The Pile

Neuron 3480 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: 0.3959. Min Range: -0.3959

Max Act: 0.3959. Min Act: -0.0000

Data Index: 905269 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2669. Min Act: -0.0000

Data Index: 654169 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2663. Min Act: -0.0000

Data Index: 434375 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1973816 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2011. Min Act: -0.0000

Data Index: 249911 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1821. Min Act: -0.0000

Data Index: 855719 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1811. Min Act: -0.0000

Data Index: 264003 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1733515 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1671. Min Act: -0.0000

Data Index: 584403 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1671. Min Act: -0.0000

Data Index: 550020 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1239665 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1540. Min Act: -0.0000

Data Index: 288594 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1619. Min Act: -0.0000

Data Index: 828540 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1659226 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1675. Min Act: -0.0000

Data Index: 713116 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1569. Min Act: -0.0000

Data Index: 227265 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1870994 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1556. Min Act: -0.0000

Data Index: 831371 (The Pile)

Max Activating Token Index: 844

Text #18

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1582. Min Act: -0.0000

Data Index: 799020 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.1637. Min Act: -0.0000

Data Index: 552430 (The Pile)

Max Activating Token Index: 554