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

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

Neuron 155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0904. Min Act: -0.0000

Data Index: 568659 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1030. Min Act: -0.0000

Data Index: 603827 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0941. Min Act: -0.0000

Data Index: 286666 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0937. Min Act: -0.0000

Data Index: 971385 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0870. Min Act: -0.0000

Data Index: 408619 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0852. Min Act: -0.0000

Data Index: 250648 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0855. Min Act: -0.0000

Data Index: 284897 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0903. Min Act: -0.0000

Data Index: 903805 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0902. Min Act: -0.0000

Data Index: 72919 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0873. Min Act: -0.0000

Data Index: 909893 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0754. Min Act: -0.0000

Data Index: 190868 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1224839 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0840. Min Act: -0.0000

Data Index: 625070 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1147212 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0841. Min Act: -0.0000

Data Index: 547165 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0841. Min Act: -0.0000

Data Index: 127124 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0841. Min Act: -0.0000

Data Index: 992023 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0809. Min Act: -0.0000

Data Index: 881766 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1317908 (C4 (Web Text))

Max Activating Token Index: 260