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

Dataset: The Pile

Neuron 3840 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: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0000

Data Index: 880070 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0625. Min Act: -0.0000

Data Index: 425647 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0587. Min Act: -0.0000

Data Index: 788986 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1940722 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0529. Min Act: -0.0000

Data Index: 323338 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1790044 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1233600 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0465. Min Act: -0.0000

Data Index: 1188785 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1174962 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0449. Min Act: -0.0000

Data Index: 992763 (The Pile)

Max Activating Token Index: 923

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0468. Min Act: -0.0000

Data Index: 1692748 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1347929 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0413. Min Act: -0.0000

Data Index: 1738017 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1657970 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0427. Min Act: -0.0000

Data Index: 462762 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0436. Min Act: -0.0000

Data Index: 1941149 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1952675 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1576261 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0399. Min Act: -0.0000

Data Index: 963067 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1727542 (The Pile)

Max Activating Token Index: 978