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

Dataset: The Pile

Neuron 866 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: 1.3883. Min Range: -1.3883

Max Act: 1.3883. Min Act: -0.0000

Data Index: 567904 (The Pile)

Max Activating Token Index: 416

Text #1

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1504542 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1141234 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2224. Min Act: -0.0000

Data Index: 59812 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2224. Min Act: -0.0000

Data Index: 788277 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1978. Min Act: -0.0000

Data Index: 350833 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1377. Min Act: -0.0000

Data Index: 857658 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1914. Min Act: -0.0000

Data Index: 891466 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1282279 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1583596 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1104111 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1714. Min Act: -0.0000

Data Index: 1698556 (The Pile)

Max Activating Token Index: 790

Text #12

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1196066 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1977892 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1448. Min Act: -0.0000

Data Index: 167065 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1577008 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1521950 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1118. Min Act: -0.0000

Data Index: 248490 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1026. Min Act: -0.0000

Data Index: 317842 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1887677 (The Pile)

Max Activating Token Index: 174