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

Dataset: The Pile

Neuron 4877 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: 1.0415. Min Range: -1.0415

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1719943 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9340. Min Act: -0.0000

Data Index: 472537 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1487337 (The Pile)

Max Activating Token Index: 247

Text #3

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1570661 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9210. Min Act: -0.0000

Data Index: 613620 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.9074. Min Act: -0.0000

Data Index: 881534 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8498. Min Act: -0.0000

Data Index: 522365 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8520. Min Act: -0.0000

Data Index: 1608495 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8458. Min Act: -0.0000

Data Index: 658902 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1219336 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8380. Min Act: -0.0000

Data Index: 548206 (The Pile)

Max Activating Token Index: 234

Text #11

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8896. Min Act: -0.0000

Data Index: 625363 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8083. Min Act: -0.0000

Data Index: 716180 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8194. Min Act: -0.0000

Data Index: 637809 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.8012. Min Act: -0.0000

Data Index: 818297 (The Pile)

Max Activating Token Index: 823

Text #15

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1920635 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7687. Min Act: -0.0000

Data Index: 713258 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1449793 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1222385 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.0415. Min Range: -1.0415

Max Act: 0.7864. Min Act: -0.0000

Data Index: 285983 (The Pile)

Max Activating Token Index: 80