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

Dataset: The Pile

Neuron 1221 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: 1.2307. Min Range: -1.2307

Max Act: 1.2307. Min Act: -0.0000

Data Index: 251737 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8072. Min Act: -0.0000

Data Index: 1757616 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.6769. Min Act: -0.0000

Data Index: 852772 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5821. Min Act: -0.0000

Data Index: 338120 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5794. Min Act: -0.0000

Data Index: 752347 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1956065 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5263. Min Act: -0.0000

Data Index: 339156 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1709482 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5465. Min Act: -0.0000

Data Index: 579215 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.5117. Min Act: -0.0000

Data Index: 631513 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1081533 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4604. Min Act: -0.0000

Data Index: 214790 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1326946 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4787. Min Act: -0.0000

Data Index: 483298 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4906. Min Act: -0.0000

Data Index: 829976 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4732. Min Act: -0.0000

Data Index: 573636 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4897. Min Act: -0.0000

Data Index: 796926 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4642. Min Act: -0.0000

Data Index: 426224 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4380. Min Act: -0.0000

Data Index: 530923 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1143627 (The Pile)

Max Activating Token Index: 720