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

Dataset: The Pile

Neuron 1961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.3094. Min Act: -0.0000

Data Index: 317922 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2917. Min Act: -0.0000

Data Index: 106798 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2563. Min Act: -0.0000

Data Index: 583451 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2631. Min Act: -0.0000

Data Index: 188805 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2732. Min Act: -0.0000

Data Index: 343597 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2673. Min Act: -0.0000

Data Index: 893778 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1719589 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1599694 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2737. Min Act: -0.0000

Data Index: 521848 (The Pile)

Max Activating Token Index: 253

Text #9

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1754754 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1234747 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1921254 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1153568 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1885580 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2581. Min Act: -0.0000

Data Index: 1991882 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1383611 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1693704 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1825230 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2625. Min Act: -0.0000

Data Index: 570551 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.3094. Min Range: -0.3094

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1527950 (The Pile)

Max Activating Token Index: 219