Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.4810. Min Act: -0.0000

Data Index: 653011 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1031379 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1647. Min Act: -0.0000

Data Index: 661631 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1022994 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1203715 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1671. Min Act: -0.0000

Data Index: 411543 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.2409. Min Act: -0.0000

Data Index: 179321 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1878. Min Act: -0.0000

Data Index: 714848 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1033244 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1740. Min Act: -0.0000

Data Index: 748763 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1648. Min Act: -0.0000

Data Index: 191815 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1222. Min Act: -0.0000

Data Index: 257714 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1271. Min Act: -0.0000

Data Index: 369418 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1350063 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1115. Min Act: -0.0000

Data Index: 22291 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.0686. Min Act: -0.0000

Data Index: 177067 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1818. Min Act: -0.0000

Data Index: 936168 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.0919. Min Act: -0.0000

Data Index: 144883 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1217275 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.4810. Min Range: -1.4810

Max Act: 1.1132. Min Act: -0.0000

Data Index: 687609 (C4 (Web Text))

Max Activating Token Index: 286