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

Dataset: The Pile

Neuron 3504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.6809. Min Act: -0.0000

Data Index: 376349 (The Pile)

Max Activating Token Index: 106

Text #1

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1066075 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1180261 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5474. Min Act: -0.0000

Data Index: 468519 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1171612 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5283. Min Act: -0.0000

Data Index: 1888512 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5127. Min Act: -0.0000

Data Index: 422668 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5106. Min Act: -0.0000

Data Index: 699154 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5070. Min Act: -0.0000

Data Index: 716800 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1714585 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.5220. Min Act: -0.0000

Data Index: 51567 (The Pile)

Max Activating Token Index: 1014

Text #11

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1559730 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4920. Min Act: -0.0000

Data Index: 871257 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4618. Min Act: -0.0000

Data Index: 205258 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4899. Min Act: -0.0000

Data Index: 241438 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1435919 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1210288 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1104953 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1191359 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.6809. Min Range: -0.6809

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1097736 (The Pile)

Max Activating Token Index: 592