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

Dataset: The Pile

Neuron 2028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3867. Min Act: -0.0000

Data Index: 369466 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1333 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1600619 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1746621 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1876078 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1455342 (The Pile)

Max Activating Token Index: 594

Text #6

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1166926 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2825. Min Act: -0.0000

Data Index: 384239 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1537771 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2577. Min Act: -0.0000

Data Index: 712582 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2633. Min Act: -0.0000

Data Index: 83270 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1896037 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2751. Min Act: -0.0000

Data Index: 424713 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2540. Min Act: -0.0000

Data Index: 577073 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2572. Min Act: -0.0000

Data Index: 544587 (The Pile)

Max Activating Token Index: 46

Text #15

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1261440 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2445. Min Act: -0.0000

Data Index: 195159 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2370. Min Act: -0.0000

Data Index: 628281 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2661. Min Act: -0.0000

Data Index: 714566 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 0.3867. Min Range: -0.3867

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1323721 (The Pile)

Max Activating Token Index: 402