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

Dataset: The Pile

Neuron 2757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1509360 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2920. Min Act: -0.0000

Data Index: 559766 (The Pile)

Max Activating Token Index: 833

Text #2

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1941. Min Act: -0.0000

Data Index: 632972 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1116952 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2057. Min Act: -0.0000

Data Index: 670244 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2002. Min Act: -0.0000

Data Index: 1237524 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.2231. Min Act: -0.0000

Data Index: 17790 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1827. Min Act: -0.0000

Data Index: 480169 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1130651 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1178. Min Act: -0.0000

Data Index: 201573 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1309350 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1564. Min Act: -0.0000

Data Index: 109736 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1659. Min Act: -0.0000

Data Index: 423310 (The Pile)

Max Activating Token Index: 404

Text #13

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1007. Min Act: -0.0000

Data Index: 942650 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0661. Min Act: -0.0000

Data Index: 229927 (The Pile)

Max Activating Token Index: 84

Text #15

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0677. Min Act: -0.0000

Data Index: 490227 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1441887 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1788472 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1722490 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.2998. Min Range: -1.2998

Max Act: 1.0468. Min Act: -0.0000

Data Index: 212158 (The Pile)

Max Activating Token Index: 935