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

Dataset: The Pile

Neuron 2960 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1425071 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.2247. Min Act: -0.0000

Data Index: 467403 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.2347. Min Act: -0.0000

Data Index: 174694 (The Pile)

Max Activating Token Index: 729

Text #3

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.2043. Min Act: -0.0000

Data Index: 361504 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.2063. Min Act: -0.0000

Data Index: 59779 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1659387 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1742. Min Act: -0.0000

Data Index: 561349 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1722934 (The Pile)

Max Activating Token Index: 652

Text #8

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1482253 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1198087 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1591978 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1907447 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0617. Min Act: -0.0000

Data Index: 308769 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1051416 (The Pile)

Max Activating Token Index: 596

Text #14

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0847. Min Act: -0.0000

Data Index: 317389 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0519. Min Act: -0.0000

Data Index: 921230 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0092. Min Act: -0.0000

Data Index: 548980 (The Pile)

Max Activating Token Index: 452

Text #17

Max Range: 1.4434. Min Range: -1.4434

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1102854 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0198. Min Act: -0.0000

Data Index: 935966 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 1.4434. Min Range: -1.4434

Max Act: 1.0156. Min Act: -0.0000

Data Index: 473289 (The Pile)

Max Activating Token Index: 898