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

Dataset: The Pile

Neuron 4317 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.5626. Min Act: -0.0000

Data Index: 726129 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1646209 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1855930 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1123976 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1909369 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0306. Min Act: -0.0000

Data Index: 119598 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9944. Min Act: -0.0000

Data Index: 385633 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1402578 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9272. Min Act: -0.0000

Data Index: 267054 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1131282 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8758. Min Act: -0.0000

Data Index: 787412 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8945. Min Act: -0.0000

Data Index: 771804 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9792. Min Act: -0.0000

Data Index: 469008 (The Pile)

Max Activating Token Index: 841

Text #13

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9350. Min Act: -0.0000

Data Index: 14756 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9267. Min Act: -0.0000

Data Index: 203261 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1583589 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8851. Min Act: -0.0000

Data Index: 535263 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1928206 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8693. Min Act: -0.0000

Data Index: 268823 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8053. Min Act: -0.0000

Data Index: 878483 (The Pile)

Max Activating Token Index: 638