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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4392 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0000

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1128. Min Act: -0.0000

Data Index: 411830 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1181. Min Act: -0.0000

Data Index: 19657 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1210. Min Act: -0.0000

Data Index: 493471 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1073. Min Act: -0.0000

Data Index: 563165 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1087. Min Act: -0.0000

Data Index: 101816 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1315197 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1350312 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1012. Min Act: -0.0000

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1095608 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0931. Min Act: -0.0000

Data Index: 691191 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1246136 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0921. Min Act: -0.0000

Data Index: 708836 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0980. Min Act: -0.0000

Data Index: 545607 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0909. Min Act: -0.0000

Data Index: 764310 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0924. Min Act: -0.0000

Data Index: 18933 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0895. Min Act: -0.0000

Data Index: 375603 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0875. Min Act: -0.0000

Data Index: 269136 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0903. Min Act: -0.0000

Data Index: 262236 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.0903. Min Act: -0.0000

Data Index: 704168 (C4 (Web Text))

Max Activating Token Index: 729