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

Dataset: The Pile

Neuron 4632 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: 1.3725. Min Range: -1.3725

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1593933 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1323726 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9361. Min Act: -0.0000

Data Index: 37031 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8902. Min Act: -0.0000

Data Index: 312553 (The Pile)

Max Activating Token Index: 470

Text #4

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7831. Min Act: -0.0000

Data Index: 728526 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1362843 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9019. Min Act: -0.0000

Data Index: 1605875 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8324. Min Act: -0.0000

Data Index: 69201 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1201315 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1934923 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7623. Min Act: -0.0000

Data Index: 171848 (The Pile)

Max Activating Token Index: 25

Text #11

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7544. Min Act: -0.0000

Data Index: 65661 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7106. Min Act: -0.0000

Data Index: 365355 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1941622 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8106. Min Act: -0.0000

Data Index: 673539 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1627645 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.6591. Min Act: -0.0000

Data Index: 306320 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.6764. Min Act: -0.0000

Data Index: 387252 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1927074 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1558118 (The Pile)

Max Activating Token Index: 656