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

Dataset: The Pile

Neuron 1020 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: 3.8221. Min Range: -3.8221

Max Act: 3.8221. Min Act: -0.0000

Data Index: 1052590 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.8081. Min Act: -0.0000

Data Index: 1822254 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.6618. Min Act: -0.0000

Data Index: 1212905 (The Pile)

Max Activating Token Index: 674

Text #3

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.4840. Min Act: -0.0000

Data Index: 480703 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.4593. Min Act: -0.0000

Data Index: 1200781 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.1687. Min Act: -0.0000

Data Index: 854018 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3822. Min Act: -0.0000

Data Index: 731298 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3861. Min Act: -0.0000

Data Index: 198020 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3996. Min Act: -0.0000

Data Index: 986925 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3624. Min Act: -0.0000

Data Index: 1702515 (The Pile)

Max Activating Token Index: 626

Text #10

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.1844. Min Act: -0.0000

Data Index: 310282 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3377. Min Act: -0.0000

Data Index: 1287622 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.1082. Min Act: -0.0000

Data Index: 919618 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.1175. Min Act: -0.0000

Data Index: 218358 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.9964. Min Act: -0.0000

Data Index: 1247401 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.8513. Min Act: -0.0000

Data Index: 1669065 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.7307. Min Act: -0.0000

Data Index: 176027 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.8178. Min Act: -0.0000

Data Index: 108910 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.9188. Min Act: -0.0000

Data Index: 1224341 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.1093. Min Act: -0.0000

Data Index: 1704460 (The Pile)

Max Activating Token Index: 791