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

Dataset: The Pile

Neuron 4512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1469657 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.5139. Min Act: -0.0000

Data Index: 671435 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1797967 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1390371 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4448. Min Act: -0.0000

Data Index: 613710 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1233827 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4071. Min Act: -0.0000

Data Index: 19387 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4473. Min Act: -0.0000

Data Index: 398728 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4036. Min Act: -0.0000

Data Index: 591477 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.4055. Min Act: -0.0000

Data Index: 155858 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1549171 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3856. Min Act: -0.0000

Data Index: 444507 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3843. Min Act: -0.0000

Data Index: 553953 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1737375 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3618. Min Act: -0.0000

Data Index: 864004 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3586. Min Act: -0.0000

Data Index: 291989 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3613. Min Act: -0.0000

Data Index: 927262 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1802387 (The Pile)

Max Activating Token Index: 666

Text #18

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3667. Min Act: -0.0000

Data Index: 870261 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.5318. Min Range: -0.5318

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1170642 (The Pile)

Max Activating Token Index: 342