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

Dataset: The Pile

Neuron 2815 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: 1.3294. Min Range: -1.3294

Max Act: 1.3294. Min Act: -0.0000

Data Index: 927937 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 1.3294. Min Range: -1.3294

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1328509 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.3294. Min Range: -1.3294

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1413976 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.9310. Min Act: -0.0000

Data Index: 637569 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1004925 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1755114 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.9366. Min Act: -0.0000

Data Index: 532747 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1692828 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1027335 (The Pile)

Max Activating Token Index: 595

Text #9

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1408888 (The Pile)

Max Activating Token Index: 727

Text #10

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1187405 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.8196. Min Act: -0.0000

Data Index: 584889 (The Pile)

Max Activating Token Index: 774

Text #12

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1350227 (The Pile)

Max Activating Token Index: 956

Text #13

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.7836. Min Act: -0.0000

Data Index: 380511 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.7682. Min Act: -0.0000

Data Index: 228327 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1039255 (The Pile)

Max Activating Token Index: 452

Text #16

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1733031 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1395566 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.8612. Min Act: -0.0000

Data Index: 290859 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 1.3294. Min Range: -1.3294

Max Act: 0.7253. Min Act: -0.0000

Data Index: 522984 (The Pile)

Max Activating Token Index: 939