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

Dataset: The Pile

Neuron 2245 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5360. Min Range: -1.5360

Max Act: 1.5360. Min Act: -0.0000

Data Index: 982177 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1271555 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.6655. Min Act: -0.0000

Data Index: 554201 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.6480. Min Act: 0.0000

Data Index: 1630057 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1660490 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1592157 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.6101. Min Act: -0.0000

Data Index: 493776 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5695. Min Act: -0.0000

Data Index: 732700 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1014007 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1806738 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5379. Min Act: -0.0000

Data Index: 300849 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5876. Min Act: -0.0000

Data Index: 645932 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1294937 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1606576 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5524. Min Act: -0.0000

Data Index: 934989 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5443. Min Act: -0.0001

Data Index: 1782208 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5308. Min Act: -0.0001

Data Index: 1466763 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5189. Min Act: -0.0001

Data Index: 1600830 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5141. Min Act: -0.0000

Data Index: 241610 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 1.5360. Min Range: -1.5360

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1407768 (The Pile)

Max Activating Token Index: 139