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

Dataset: The Pile

Neuron 3115 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0681. Min Range: -1.0681

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1651672 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 1.0681. Min Range: -1.0681

Max Act: 1.0296. Min Act: 0.0000

Data Index: 81222 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9047. Min Act: 0.0000

Data Index: 809082 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1580678 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8656. Min Act: 0.0000

Data Index: 303203 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1221247 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7704. Min Act: 0.0000

Data Index: 17616 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8244. Min Act: 0.0001

Data Index: 576860 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8052. Min Act: -0.0000

Data Index: 772447 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1412000 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1978540 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8023. Min Act: 0.0000

Data Index: 1787425 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7782. Min Act: -0.0000

Data Index: 670147 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1439917 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8184. Min Act: -0.0000

Data Index: 901855 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.8235. Min Act: 0.0000

Data Index: 1688524 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7901. Min Act: -0.0000

Data Index: 161874 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.9049. Min Act: -0.0000

Data Index: 307489 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1559926 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.0681. Min Range: -1.0681

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1796162 (The Pile)

Max Activating Token Index: 278