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

Dataset: The Pile

Neuron 2972 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: 0.2457. Min Range: -0.2457

Max Act: 0.2457. Min Act: -0.0000

Data Index: 278669 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1330582 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2127. Min Act: -0.0000

Data Index: 961297 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2181. Min Act: -0.0000

Data Index: 309760 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1919187 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1054285 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2028. Min Act: -0.0000

Data Index: 670682 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2078. Min Act: -0.0000

Data Index: 490930 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2008. Min Act: -0.0000

Data Index: 523858 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1022556 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.2123. Min Act: -0.0000

Data Index: 214202 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1971. Min Act: -0.0000

Data Index: 149245 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1945. Min Act: -0.0000

Data Index: 599426 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1793. Min Act: -0.0000

Data Index: 884548 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1077412 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1898. Min Act: -0.0000

Data Index: 484708 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1781. Min Act: -0.0000

Data Index: 247162 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1717377 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1252682 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.2457. Min Range: -0.2457

Max Act: 0.1869. Min Act: -0.0000

Data Index: 779520 (The Pile)

Max Activating Token Index: 558