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

Dataset: The Pile

Neuron 857 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1752277 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1647772 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.7051. Min Act: -0.0000

Data Index: 857353 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1246888 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1229050 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5748. Min Act: -0.0000

Data Index: 136027 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5642. Min Act: -0.0000

Data Index: 788986 (The Pile)

Max Activating Token Index: 825

Text #7

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.6243. Min Act: -0.0000

Data Index: 287123 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5633. Min Act: -0.0000

Data Index: 894897 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5189. Min Act: -0.0000

Data Index: 256700 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5166. Min Act: -0.0000

Data Index: 422229 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1375421 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1958433 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1205380 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5050. Min Act: -0.0000

Data Index: 789961 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1677815 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5024. Min Act: -0.0000

Data Index: 198679 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5306. Min Act: -0.0000

Data Index: 965786 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1004822 (The Pile)

Max Activating Token Index: 851

Text #19

Max Range: 0.7051. Min Range: -0.7051

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1201633 (The Pile)

Max Activating Token Index: 130