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

Dataset: The Pile

Neuron 2523 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: 5.2506. Min Range: -5.2506

Max Act: 5.2506. Min Act: -0.0000

Data Index: 1876408 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.9738. Min Act: -0.0000

Data Index: 1027581 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.5104. Min Act: -0.0000

Data Index: 149752 (The Pile)

Max Activating Token Index: 796

Text #3

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.5187. Min Act: -0.0000

Data Index: 183185 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.4691. Min Act: -0.0000

Data Index: 163717 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.6728. Min Act: -0.0000

Data Index: 1910413 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.5962. Min Act: -0.0000

Data Index: 1124591 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.1459. Min Act: -0.0000

Data Index: 1871270 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.1832. Min Act: -0.0000

Data Index: 1829243 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.3442. Min Act: -0.0000

Data Index: 1068432 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.4447. Min Act: -0.0000

Data Index: 238147 (The Pile)

Max Activating Token Index: 405

Text #11

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.2046. Min Act: -0.0000

Data Index: 1238930 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.1954. Min Act: -0.0000

Data Index: 393795 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.2815. Min Act: -0.0000

Data Index: 1791585 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.2982. Min Act: -0.0000

Data Index: 977874 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.0855. Min Act: -0.0000

Data Index: 1035930 (The Pile)

Max Activating Token Index: 589

Text #16

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.2489. Min Act: -0.0000

Data Index: 1917686 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 5.2506. Min Range: -5.2506

Max Act: 4.0465. Min Act: -0.0000

Data Index: 795903 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 5.2506. Min Range: -5.2506

Max Act: 3.7221. Min Act: -0.0000

Data Index: 1281471 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 5.2506. Min Range: -5.2506

Max Act: 3.8805. Min Act: -0.0000

Data Index: 1778796 (The Pile)

Max Activating Token Index: 532