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

Dataset: The Pile

Neuron 2075 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: 0.3446. Min Range: -0.3446

Max Act: 0.3446. Min Act: -0.0000

Data Index: 658308 (The Pile)

Max Activating Token Index: 737

Text #1

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1264013 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1765660 (The Pile)

Max Activating Token Index: 720

Text #3

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2181. Min Act: -0.0000

Data Index: 945159 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1326017 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1043003 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1765. Min Act: -0.0000

Data Index: 756599 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1708979 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1816. Min Act: -0.0000

Data Index: 53759 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1586. Min Act: -0.0000

Data Index: 164139 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1433164 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1662. Min Act: -0.0000

Data Index: 695168 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1839678 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1626. Min Act: -0.0000

Data Index: 769834 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1642. Min Act: -0.0000

Data Index: 100525 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1477. Min Act: -0.0000

Data Index: 550646 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1585. Min Act: -0.0000

Data Index: 120738 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1530. Min Act: -0.0000

Data Index: 279304 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1844597 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.3446. Min Range: -0.3446

Max Act: 0.1379. Min Act: -0.0000

Data Index: 784699 (The Pile)

Max Activating Token Index: 573