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

Dataset: The Pile

Neuron 5014 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2076. Min Range: -1.2076

Max Act: 1.2076. Min Act: -0.0000

Data Index: 374653 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 1.2076. Min Range: -1.2076

Max Act: 1.0090. Min Act: -0.0000

Data Index: 397162 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9448. Min Act: -0.0000

Data Index: 375987 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9743. Min Act: -0.0000

Data Index: 537556 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1814137 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1842667 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9016. Min Act: -0.0000

Data Index: 595249 (The Pile)

Max Activating Token Index: 432

Text #7

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1806561 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1930988 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1062366 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8777. Min Act: -0.0000

Data Index: 704663 (The Pile)

Max Activating Token Index: 7

Text #11

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8340. Min Act: -0.0000

Data Index: 1730137 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1553132 (The Pile)

Max Activating Token Index: 55

Text #13

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7856. Min Act: -0.0000

Data Index: 964735 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8017. Min Act: -0.0000

Data Index: 1006111 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.8019. Min Act: -0.0000

Data Index: 675992 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7696. Min Act: -0.0000

Data Index: 257056 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7767. Min Act: -0.0000

Data Index: 439946 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1379964 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 1.2076. Min Range: -1.2076

Max Act: 0.7462. Min Act: -0.0000

Data Index: 784251 (The Pile)

Max Activating Token Index: 620