Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3258 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1940295 (The Pile)

Max Activating Token Index: 651

Text #1

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1446625 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1844680 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3521. Min Act: -0.0000

Data Index: 1217653 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3467. Min Act: -0.0000

Data Index: 864869 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1469701 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2832. Min Act: -0.0000

Data Index: 5892 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3065. Min Act: -0.0000

Data Index: 991000 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.3159. Min Act: -0.0000

Data Index: 216858 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1275977 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2821. Min Act: -0.0000

Data Index: 495439 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2736. Min Act: -0.0000

Data Index: 24313 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2572. Min Act: -0.0000

Data Index: 885026 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2557. Min Act: -0.0000

Data Index: 134851 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1454683 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2560. Min Act: -0.0000

Data Index: 226037 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2425. Min Act: -0.0000

Data Index: 492126 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2604. Min Act: -0.0000

Data Index: 412568 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1846747 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1373451 (The Pile)

Max Activating Token Index: 366