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

Dataset: The Pile

Neuron 1717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1531921 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2127. Min Act: -0.0000

Data Index: 865249 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0877. Min Act: -0.0000

Data Index: 487103 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1836765 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.1422. Min Act: -0.0000

Data Index: 432492 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1238996 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1573980 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1495328 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0961. Min Act: -0.0000

Data Index: 221288 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0341. Min Act: -0.0000

Data Index: 388530 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0500. Min Act: -0.0000

Data Index: 388423 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 1.2847. Min Range: -1.2847

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1257440 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9306. Min Act: -0.0000

Data Index: 261130 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9022. Min Act: -0.0000

Data Index: 594280 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1891079 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9861. Min Act: -0.0000

Data Index: 766116 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1601441 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8914. Min Act: -0.0000

Data Index: 699613 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.8260. Min Act: -0.0000

Data Index: 480343 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 1.2847. Min Range: -1.2847

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1022226 (The Pile)

Max Activating Token Index: 470