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

Dataset: The Pile

Neuron 3237 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: 0.2743. Min Range: -0.2743

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1069263 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.2150. Min Act: -0.0000

Data Index: 999090 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1205223 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1768355 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1842. Min Act: -0.0000

Data Index: 27949 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1934064 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1738. Min Act: -0.0000

Data Index: 67268 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1517925 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1971627 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1618. Min Act: -0.0000

Data Index: 652704 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1622. Min Act: -0.0000

Data Index: 39788 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1579. Min Act: -0.0000

Data Index: 629576 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1610. Min Act: -0.0000

Data Index: 102109 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1619. Min Act: -0.0000

Data Index: 38959 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1141927 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1513. Min Act: -0.0000

Data Index: 510557 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1465. Min Act: -0.0000

Data Index: 643743 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1459467 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1653898 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.2743. Min Range: -0.2743

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1626620 (The Pile)

Max Activating Token Index: 219