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

Dataset: The Pile

Neuron 2725 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: 4.0324. Min Range: -4.0324

Max Act: 4.0324. Min Act: -0.0000

Data Index: 1841863 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.8179. Min Act: -0.0000

Data Index: 1941706 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4828. Min Act: -0.0000

Data Index: 765839 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4796. Min Act: -0.0000

Data Index: 1270285 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.5495. Min Act: -0.0000

Data Index: 775955 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.5188. Min Act: -0.0000

Data Index: 1872426 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.5109. Min Act: -0.0000

Data Index: 1524713 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4443. Min Act: -0.0000

Data Index: 1110287 (The Pile)

Max Activating Token Index: 698

Text #8

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.3353. Min Act: -0.0000

Data Index: 709609 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.2963. Min Act: -0.0000

Data Index: 50491 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4644. Min Act: -0.0000

Data Index: 963665 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.6047. Min Act: -0.0000

Data Index: 515734 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4386. Min Act: -0.0000

Data Index: 1680806 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4272. Min Act: -0.0000

Data Index: 355996 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4141. Min Act: -0.0000

Data Index: 1035757 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.5402. Min Act: -0.0000

Data Index: 459676 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.3769. Min Act: -0.0000

Data Index: 992713 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.3933. Min Act: -0.0000

Data Index: 625847 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.4688. Min Act: -0.0000

Data Index: 1553828 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 4.0324. Min Range: -4.0324

Max Act: 3.3162. Min Act: -0.0000

Data Index: 296723 (The Pile)

Max Activating Token Index: 480