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

Dataset: The Pile

Neuron 3640 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: 5.7317. Min Range: -5.7317

Max Act: 5.5487. Min Act: -0.0000

Data Index: 512388 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.3905. Min Act: -0.0000

Data Index: 359718 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.7317. Min Act: -0.0000

Data Index: 836530 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.4012. Min Act: -0.0000

Data Index: 1585169 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.5077. Min Act: -0.0000

Data Index: 1430742 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.8757. Min Act: -0.0000

Data Index: 1009967 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.2494. Min Act: -0.0000

Data Index: 1325018 (The Pile)

Max Activating Token Index: 685

Text #7

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.3131. Min Act: -0.0000

Data Index: 1226918 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 5.7317. Min Range: -5.7317

Max Act: 5.1407. Min Act: -0.0000

Data Index: 508393 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.8995. Min Act: -0.0000

Data Index: 664876 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.7252. Min Act: -0.0000

Data Index: 914123 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.5028. Min Act: -0.0000

Data Index: 1042473 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.5577. Min Act: -0.0000

Data Index: 207506 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.3597. Min Act: -0.0000

Data Index: 1470391 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.3235. Min Act: -0.0000

Data Index: 427252 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.1033. Min Act: -0.0000

Data Index: 292403 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 5.7317. Min Range: -5.7317

Max Act: 3.9007. Min Act: -0.0000

Data Index: 1045319 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 5.7317. Min Range: -5.7317

Max Act: 3.7792. Min Act: -0.0000

Data Index: 975928 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.1293. Min Act: -0.0000

Data Index: 622866 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 5.7317. Min Range: -5.7317

Max Act: 4.2949. Min Act: -0.0000

Data Index: 1829702 (The Pile)

Max Activating Token Index: 808