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

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

Neuron 436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1184. Min Act: -0.0000

Data Index: 80167 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1009520 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1244790 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0918. Min Act: -0.0001

Data Index: 787993 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0913. Min Act: -0.0001

Data Index: 943284 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0913. Min Act: -0.0000

Data Index: 390078 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0793. Min Act: -0.0001

Data Index: 755770 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0867. Min Act: -0.0001

Data Index: 649841 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0805. Min Act: -0.0000

Data Index: 884635 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1587375 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1268421 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1597628 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0790. Min Act: -0.0000

Data Index: 28024 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0814. Min Act: -0.0000

Data Index: 745596 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0805. Min Act: -0.0001

Data Index: 348999 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0800. Min Act: -0.0000

Data Index: 899779 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0823. Min Act: -0.0000

Data Index: 102507 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1241617 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0796. Min Act: -0.0000

Data Index: 539403 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0784. Min Act: -0.0000

Data Index: 926265 (C4 (Web Text))

Max Activating Token Index: 408