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

Dataset: The Pile

Neuron 3659 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: 1.9498. Min Range: -1.9498

Max Act: 1.8748. Min Act: -0.0000

Data Index: 1966843 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.8935. Min Act: -0.0000

Data Index: 140272 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.9498. Min Act: -0.0000

Data Index: 1592731 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.6796. Min Act: -0.0000

Data Index: 614227 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5271. Min Act: -0.0000

Data Index: 1175303 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.6171. Min Act: -0.0000

Data Index: 837182 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5214. Min Act: -0.0000

Data Index: 722555 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4175. Min Act: -0.0000

Data Index: 850162 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4465. Min Act: -0.0000

Data Index: 4577 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5122. Min Act: -0.0000

Data Index: 481092 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.3178. Min Act: -0.0000

Data Index: 286715 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4635. Min Act: -0.0000

Data Index: 320675 (The Pile)

Max Activating Token Index: 898

Text #12

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.5045. Min Act: -0.0001

Data Index: 1385808 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4307. Min Act: -0.0000

Data Index: 587928 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1578457 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.3340. Min Act: -0.0000

Data Index: 1614824 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1229685 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.4384. Min Act: -0.0000

Data Index: 1708202 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.2867. Min Act: -0.0000

Data Index: 373183 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.9498. Min Range: -1.9498

Max Act: 1.2638. Min Act: -0.0000

Data Index: 490089 (The Pile)

Max Activating Token Index: 642