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

Dataset: The Pile

Neuron 490 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.6880. Min Act: -0.0000

Data Index: 1330782 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.4470. Min Act: -0.0000

Data Index: 459356 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1178144 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.4499. Min Act: -0.0000

Data Index: 647849 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3962. Min Act: -0.0000

Data Index: 955325 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.4715. Min Act: -0.0000

Data Index: 407173 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.4767. Min Act: -0.0000

Data Index: 663053 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1616870 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3537. Min Act: -0.0000

Data Index: 774236 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2914. Min Act: -0.0000

Data Index: 1317537 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3350. Min Act: -0.0000

Data Index: 591269 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.3397. Min Act: -0.0000

Data Index: 902985 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2955. Min Act: -0.0000

Data Index: 265450 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1915806 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2456. Min Act: 0.0002

Data Index: 1326223 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2236. Min Act: -0.0000

Data Index: 16996 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1419797 (The Pile)

Max Activating Token Index: 335

Text #17

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.1708. Min Act: -0.0000

Data Index: 120112 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2779. Min Act: -0.0000

Data Index: 712450 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 1.6880. Min Range: -1.6880

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1107347 (The Pile)

Max Activating Token Index: 684