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

Dataset: The Pile

Neuron 3616 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: 1.5199. Min Range: -1.5199

Max Act: 1.4034. Min Act: -0.0000

Data Index: 1155352 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1672581 (The Pile)

Max Activating Token Index: 970

Text #2

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1810800 (The Pile)

Max Activating Token Index: 488

Text #3

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.2884. Min Act: -0.0000

Data Index: 741431 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.3558. Min Act: -0.0000

Data Index: 1108327 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1383746 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.5199. Min Act: -0.0000

Data Index: 551021 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1661. Min Act: -0.0000

Data Index: 996572 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1643. Min Act: -0.0000

Data Index: 238292 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1954886 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.2437. Min Act: -0.0000

Data Index: 680118 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1055993 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.2162. Min Act: -0.0000

Data Index: 863255 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.2340. Min Act: -0.0000

Data Index: 353976 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1069249 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1831. Min Act: -0.0000

Data Index: 492522 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1993. Min Act: -0.0000

Data Index: 958982 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1761348 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0852. Min Act: -0.0000

Data Index: 452072 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1389325 (The Pile)

Max Activating Token Index: 118