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

Dataset: The Pile

Neuron 4922 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: 1.6297. Min Range: -1.6297

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1073787 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1077375 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1658813 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.4197. Min Act: -0.0000

Data Index: 155979 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2993. Min Act: -0.0000

Data Index: 907753 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1767305 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.4305. Min Act: -0.0000

Data Index: 1893257 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2180. Min Act: -0.0000

Data Index: 96273 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2286. Min Act: -0.0000

Data Index: 1606003 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1787971 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1491939 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2203. Min Act: -0.0000

Data Index: 1253921 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2414. Min Act: -0.0000

Data Index: 578004 (The Pile)

Max Activating Token Index: 177

Text #13

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2877. Min Act: -0.0000

Data Index: 447416 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1269982 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1600672 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2181. Min Act: -0.0000

Data Index: 1172745 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2967. Min Act: -0.0000

Data Index: 183269 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1886631 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 1.6297. Min Range: -1.6297

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1936530 (The Pile)

Max Activating Token Index: 543