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

Dataset: The Pile

Neuron 2450 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: 1.4022. Min Range: -1.4022

Max Act: 1.4022. Min Act: -0.0000

Data Index: 529861 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1331108 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0215. Min Act: -0.0000

Data Index: 218078 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0363. Min Act: -0.0000

Data Index: 1782542 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0717. Min Act: -0.0000

Data Index: 156233 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1949357 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1457. Min Act: -0.0000

Data Index: 80061 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0853. Min Act: -0.0000

Data Index: 519333 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1155888 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0371. Min Act: -0.0000

Data Index: 431313 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0318. Min Act: -0.0000

Data Index: 723109 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.1337. Min Act: -0.0000

Data Index: 214596 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9810. Min Act: -0.0000

Data Index: 669706 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0153. Min Act: -0.0000

Data Index: 834532 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9690. Min Act: -0.0000

Data Index: 79654 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0141. Min Act: -0.0000

Data Index: 512578 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1802937 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1733268 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 1.4022. Min Range: -1.4022

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1910863 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 1.4022. Min Range: -1.4022

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1160915 (The Pile)

Max Activating Token Index: 1012