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

Dataset: The Pile

Neuron 783 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: 1.0403. Min Range: -1.0403

Max Act: 0.9793. Min Act: -0.0000

Data Index: 51433 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1366958 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9667. Min Act: -0.0000

Data Index: 921910 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.0403. Min Range: -1.0403

Max Act: 1.0403. Min Act: -0.0000

Data Index: 527006 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1518541 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8446. Min Act: -0.0000

Data Index: 732931 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1807439 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7955. Min Act: -0.0000

Data Index: 838936 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1357971 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1299310 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1446633 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1882228 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1149288 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.8457. Min Act: -0.0000

Data Index: 613528 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7953. Min Act: -0.0000

Data Index: 337323 (The Pile)

Max Activating Token Index: 731

Text #15

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6663. Min Act: -0.0000

Data Index: 530158 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7106. Min Act: -0.0000

Data Index: 808067 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.6800. Min Act: -0.0000

Data Index: 259381 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7255. Min Act: 0.0000

Data Index: 914469 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.0403. Min Range: -1.0403

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1212356 (The Pile)

Max Activating Token Index: 827