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

Dataset: The Pile

Neuron 4413 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: 0.3212. Min Range: -0.3212

Max Act: 0.2307. Min Act: -0.0000

Data Index: 618250 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3212. Min Act: -0.0000

Data Index: 4698 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1713595 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2900. Min Act: -0.0000

Data Index: 713799 (The Pile)

Max Activating Token Index: 732

Text #4

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2892. Min Act: -0.0000

Data Index: 555308 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1511496 (The Pile)

Max Activating Token Index: 494

Text #6

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2679. Min Act: -0.0000

Data Index: 898907 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2615. Min Act: -0.0000

Data Index: 183858 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2628. Min Act: -0.0000

Data Index: 621523 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2000. Min Act: -0.0000

Data Index: 25577 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2508. Min Act: -0.0000

Data Index: 847260 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2453. Min Act: -0.0000

Data Index: 995145 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2456. Min Act: -0.0000

Data Index: 825551 (The Pile)

Max Activating Token Index: 368

Text #13

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2332. Min Act: -0.0000

Data Index: 588374 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2350. Min Act: -0.0000

Data Index: 923661 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2575. Min Act: -0.0000

Data Index: 853912 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1322961 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2381. Min Act: -0.0000

Data Index: 89671 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1166348 (The Pile)

Max Activating Token Index: 548

Text #19

Max Range: 0.3212. Min Range: -0.3212

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1907055 (The Pile)

Max Activating Token Index: 839