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

Dataset: The Pile

Neuron 1893 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1399717 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.4509. Min Act: -0.0000

Data Index: 1453284 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1083737 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3063. Min Act: -0.0000

Data Index: 1515425 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3287. Min Act: -0.0000

Data Index: 1269064 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.3042. Min Act: -0.0000

Data Index: 283856 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1613158 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.2210. Min Act: -0.0000

Data Index: 1205771 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1317. Min Act: -0.0000

Data Index: 1421893 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1558417 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1899328 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.2061. Min Act: -0.0000

Data Index: 281393 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1035. Min Act: -0.0000

Data Index: 459824 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1442. Min Act: -0.0000

Data Index: 1929748 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1972472 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1496000 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1981264 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 1.4509. Min Range: -1.4509

Max Act: 1.1066. Min Act: -0.0000

Data Index: 281091 (The Pile)

Max Activating Token Index: 667

Text #18

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1679823 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 1.4509. Min Range: -1.4509

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1624652 (The Pile)

Max Activating Token Index: 975