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

Dataset: The Pile

Neuron 1267 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: 0.3736. Min Range: -0.3736

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1401896 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1414508 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1951459 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2906. Min Act: -0.0000

Data Index: 708947 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1548566 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2453. Min Act: -0.0000

Data Index: 893877 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1541081 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1985799 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2584. Min Act: -0.0000

Data Index: 560961 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2606. Min Act: -0.0000

Data Index: 709592 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1683630 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1234508 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1590200 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2409. Min Act: -0.0000

Data Index: 434957 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2353. Min Act: -0.0000

Data Index: 755005 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1010279 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1103573 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1762921 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2275. Min Act: -0.0000

Data Index: 608855 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.3736. Min Range: -0.3736

Max Act: 0.2440. Min Act: -0.0000

Data Index: 291556 (The Pile)

Max Activating Token Index: 252