Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 286 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1264. Min Range: -1.1264

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1905180 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 1.1264. Min Range: -1.1264

Max Act: 1.0357. Min Act: -0.0000

Data Index: 323036 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.1264. Min Range: -1.1264

Max Act: 1.0035. Min Act: -0.0000

Data Index: 713921 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 1.1264. Min Range: -1.1264

Max Act: 1.0016. Min Act: -0.0000

Data Index: 107946 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9723. Min Act: -0.0000

Data Index: 504341 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 1.1264. Min Range: -1.1264

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1012065 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1260582 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1806957 (The Pile)

Max Activating Token Index: 889

Text #8

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1619442 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9287. Min Act: -0.0000

Data Index: 779065 (The Pile)

Max Activating Token Index: 578

Text #10

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9189. Min Act: -0.0000

Data Index: 362990 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8897. Min Act: -0.0000

Data Index: 973734 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9142. Min Act: -0.0000

Data Index: 285030 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9079. Min Act: -0.0000

Data Index: 900038 (The Pile)

Max Activating Token Index: 703

Text #14

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8383. Min Act: 0.0000

Data Index: 1714603 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8864. Min Act: -0.0000

Data Index: 728858 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.9161. Min Act: 0.0000

Data Index: 761895 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1898867 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1838680 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.1264. Min Range: -1.1264

Max Act: 0.8049. Min Act: -0.0000

Data Index: 560638 (The Pile)

Max Activating Token Index: 501