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

Dataset: The Pile

Neuron 912 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: 1.7804. Min Range: -1.7804

Max Act: 1.7804. Min Act: -0.0000

Data Index: 1702416 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4552. Min Act: -0.0000

Data Index: 704147 (The Pile)

Max Activating Token Index: 432

Text #2

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1438796 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.6028. Min Act: -0.0000

Data Index: 1460508 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4479. Min Act: -0.0001

Data Index: 391977 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4225. Min Act: -0.0000

Data Index: 378064 (The Pile)

Max Activating Token Index: 270

Text #6

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1079524 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1372689 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3096. Min Act: -0.0000

Data Index: 440799 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3714. Min Act: -0.0000

Data Index: 1592409 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1729728 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1603637 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1278135 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3308. Min Act: -0.0000

Data Index: 322737 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1210067 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1121541 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.2808. Min Act: -0.0000

Data Index: 768149 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.3791. Min Act: -0.0000

Data Index: 153271 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.2595. Min Act: -0.0000

Data Index: 770081 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 1.7804. Min Range: -1.7804

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1909519 (The Pile)

Max Activating Token Index: 611