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

Dataset: The Pile

Neuron 4706 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4235. Min Range: -3.4235

Max Act: 3.2061. Min Act: -0.0000

Data Index: 962933 (The Pile)

Max Activating Token Index: 676

Text #1

Max Range: 3.4235. Min Range: -3.4235

Max Act: 3.4235. Min Act: -0.0000

Data Index: 1017993 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.5322. Min Act: -0.0000

Data Index: 1492314 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.6891. Min Act: -0.0000

Data Index: 256241 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 3.4235. Min Range: -3.4235

Max Act: 3.1048. Min Act: -0.0000

Data Index: 28420 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 3.4235. Min Range: -3.4235

Max Act: 3.3383. Min Act: -0.0000

Data Index: 1774745 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1411938 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 3.4235. Min Range: -3.4235

Max Act: 3.0792. Min Act: -0.0000

Data Index: 152700 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 3.4235. Min Range: -3.4235

Max Act: 3.0825. Min Act: -0.0000

Data Index: 768972 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9333. Min Act: -0.0000

Data Index: 616455 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9098. Min Act: -0.0000

Data Index: 1886164 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9997. Min Act: -0.0000

Data Index: 1785500 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.7625. Min Act: -0.0000

Data Index: 1159262 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9886. Min Act: -0.0000

Data Index: 1673805 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.8610. Min Act: -0.0000

Data Index: 261300 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9599. Min Act: -0.0000

Data Index: 1318509 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.9942. Min Act: -0.0000

Data Index: 546277 (The Pile)

Max Activating Token Index: 980

Text #17

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.5929. Min Act: -0.0000

Data Index: 856990 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.7833. Min Act: -0.0000

Data Index: 232373 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 3.4235. Min Range: -3.4235

Max Act: 2.5659. Min Act: -0.0000

Data Index: 1479795 (The Pile)

Max Activating Token Index: 538