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

Dataset: The Pile

Neuron 2299 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: 1.2997. Min Range: -1.2997

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1195641 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.2652. Min Act: -0.0000

Data Index: 857116 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.1856. Min Act: -0.0000

Data Index: 968979 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1011662 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0627. Min Act: -0.0000

Data Index: 747554 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0084. Min Act: -0.0000

Data Index: 837133 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8672. Min Act: -0.0000

Data Index: 893316 (The Pile)

Max Activating Token Index: 276

Text #7

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8617. Min Act: -0.0000

Data Index: 44250 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1063715 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1368848 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8877. Min Act: -0.0000

Data Index: 87903 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9240. Min Act: -0.0000

Data Index: 29464 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1621158 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1898759 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1667827 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8617. Min Act: -0.0000

Data Index: 186885 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8547. Min Act: -0.0000

Data Index: 405002 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8361. Min Act: -0.0000

Data Index: 346976 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1966723 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1516479 (The Pile)

Max Activating Token Index: 81