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

Dataset: The Pile

Neuron 3779 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1955153 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8053. Min Act: -0.0000

Data Index: 716500 (The Pile)

Max Activating Token Index: 396

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7483. Min Act: -0.0000

Data Index: 726651 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1652943 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6638. Min Act: -0.0000

Data Index: 432736 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1290989 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7108. Min Act: -0.0000

Data Index: 581143 (The Pile)

Max Activating Token Index: 381

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1202191 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1747197 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1108095 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6406. Min Act: -0.0000

Data Index: 698842 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1562193 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1409501 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1904387 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1781030 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1350433 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1451319 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1171752 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6420. Min Act: -0.0000

Data Index: 517412 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1666315 (The Pile)

Max Activating Token Index: 101