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

Dataset: The Pile

Neuron 3692 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: 1.5425. Min Range: -1.5425

Max Act: 1.5425. Min Act: -0.0000

Data Index: 1491564 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.2851. Min Act: -0.0000

Data Index: 900004 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.2716. Min Act: -0.0000

Data Index: 1369200 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1061380 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1899334 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.3112. Min Act: -0.0000

Data Index: 74674 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1646970 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.1517. Min Act: -0.0000

Data Index: 836859 (The Pile)

Max Activating Token Index: 903

Text #8

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.0459. Min Act: -0.0000

Data Index: 1538071 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.1201. Min Act: -0.0000

Data Index: 396314 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1820211 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.8827. Min Act: -0.0000

Data Index: 267300 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.0909. Min Act: -0.0000

Data Index: 1019753 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 1.5425. Min Range: -1.5425

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1380874 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.9293. Min Act: -0.0000

Data Index: 385540 (The Pile)

Max Activating Token Index: 773

Text #15

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.9836. Min Act: -0.0000

Data Index: 963706 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.9900. Min Act: -0.0000

Data Index: 443289 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1882971 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.7536. Min Act: -0.0000

Data Index: 757868 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.5425. Min Range: -1.5425

Max Act: 0.8362. Min Act: -0.0000

Data Index: 447235 (The Pile)

Max Activating Token Index: 735