Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1943. Min Act: -0.0000

Data Index: 496092 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1916. Min Act: -0.0000

Data Index: 640656 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1820. Min Act: -0.0001

Data Index: 448625 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1489156 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1257960 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1196654 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1644. Min Act: -0.0000

Data Index: 341604 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1625. Min Act: -0.0000

Data Index: 651965 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1584041 (The Pile)

Max Activating Token Index: 153

Text #9

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1704. Min Act: -0.0001

Data Index: 107616 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1630. Min Act: -0.0001

Data Index: 474116 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1984981 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1357078 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1557312 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1647. Min Act: -0.0001

Data Index: 800526 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1701. Min Act: -0.0000

Data Index: 174535 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1572. Min Act: -0.0000

Data Index: 125208 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1624. Min Act: -0.0000

Data Index: 210098 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1625. Min Act: -0.0001

Data Index: 773186 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.1943. Min Range: -0.1943

Max Act: 0.1611. Min Act: -0.0000

Data Index: 244986 (The Pile)

Max Activating Token Index: 748