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

Dataset: The Pile

Neuron 281 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.5596. Min Act: -0.0000

Data Index: 996406 (The Pile)

Max Activating Token Index: 216

Text #1

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.2802. Min Act: -0.0000

Data Index: 607745 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.1623. Min Act: -0.0000

Data Index: 1442851 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.1609. Min Act: -0.0000

Data Index: 160439 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.4215. Min Act: -0.0000

Data Index: 1592392 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.0049. Min Act: -0.0000

Data Index: 1630437 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.8328. Min Act: -0.0000

Data Index: 1118843 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.0577. Min Act: -0.0000

Data Index: 863675 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.0224. Min Act: -0.0000

Data Index: 271744 (The Pile)

Max Activating Token Index: 606

Text #9

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.8523. Min Act: -0.0000

Data Index: 1644390 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.1436. Min Act: -0.0000

Data Index: 433180 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.8565. Min Act: -0.0000

Data Index: 861999 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.6482. Min Act: -0.0000

Data Index: 1762944 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.8962. Min Act: -0.0000

Data Index: 1961812 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.1814. Min Act: -0.0000

Data Index: 606849 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.6110. Min Act: -0.0000

Data Index: 1528747 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 3.5596. Min Range: -3.5596

Max Act: 3.0037. Min Act: -0.0000

Data Index: 1317072 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.9611. Min Act: -0.0000

Data Index: 1701079 (The Pile)

Max Activating Token Index: 573

Text #18

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.9364. Min Act: -0.0000

Data Index: 1205397 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 3.5596. Min Range: -3.5596

Max Act: 2.8949. Min Act: -0.0000

Data Index: 690008 (The Pile)

Max Activating Token Index: 132