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

Dataset: The Pile

Neuron 5092 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0000

Data Index: 24146 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0720. Min Act: -0.0000

Data Index: 342433 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0708. Min Act: -0.0000

Data Index: 269329 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1804588 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1193073 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1301698 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0565. Min Act: -0.0000

Data Index: 755513 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1438336 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1061312 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1493192 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0540. Min Act: -0.0000

Data Index: 1382533 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0543. Min Act: -0.0000

Data Index: 40280 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1678538 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1883269 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0513. Min Act: -0.0000

Data Index: 53683 (The Pile)

Max Activating Token Index: 386

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1407972 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0393. Min Act: -0.0000

Data Index: 970080 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0461. Min Act: -0.0000

Data Index: 790651 (The Pile)

Max Activating Token Index: 308

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0464. Min Act: -0.0000

Data Index: 700042 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0493. Min Act: -0.0000

Data Index: 379972 (The Pile)

Max Activating Token Index: 854