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

Dataset: The Pile

Neuron 770 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: 3.1404. Min Range: -3.1404

Max Act: 3.1404. Min Act: -0.0001

Data Index: 1283023 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 3.1404. Min Range: -3.1404

Max Act: 3.0735. Min Act: -0.0001

Data Index: 750137 (The Pile)

Max Activating Token Index: 320

Text #2

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.5839. Min Act: -0.0000

Data Index: 1858404 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.3606. Min Act: -0.0000

Data Index: 1444414 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.0688. Min Act: -0.0000

Data Index: 312694 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1693. Min Act: -0.0000

Data Index: 1263460 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1831. Min Act: -0.0000

Data Index: 1039734 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1677. Min Act: -0.0001

Data Index: 1147183 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 3.1404. Min Range: -3.1404

Max Act: 1.9684. Min Act: -0.0000

Data Index: 1092180 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 3.1404. Min Range: -3.1404

Max Act: 1.9727. Min Act: -0.0000

Data Index: 1898110 (The Pile)

Max Activating Token Index: 197

Text #10

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.2579. Min Act: -0.0000

Data Index: 1896474 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1005. Min Act: -0.0000

Data Index: 1151962 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 3.1404. Min Range: -3.1404

Max Act: 1.9286. Min Act: -0.0000

Data Index: 1078080 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1709. Min Act: -0.0001

Data Index: 1855508 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.0101. Min Act: -0.0000

Data Index: 1954345 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 3.1404. Min Range: -3.1404

Max Act: 1.9938. Min Act: -0.0000

Data Index: 1721002 (The Pile)

Max Activating Token Index: 820

Text #16

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.1925. Min Act: -0.0000

Data Index: 1377074 (The Pile)

Max Activating Token Index: 692

Text #17

Max Range: 3.1404. Min Range: -3.1404

Max Act: 1.9842. Min Act: -0.0000

Data Index: 952547 (The Pile)

Max Activating Token Index: 647

Text #18

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.0402. Min Act: -0.0000

Data Index: 1642986 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.0962. Min Act: -0.0000

Data Index: 663904 (The Pile)

Max Activating Token Index: 560