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

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

Neuron 3305 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: 1.2573. Min Range: -1.2573

Max Act: 1.2573. Min Act: -0.0000

Data Index: 919747 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1227435 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.2153. Min Act: -0.0000

Data Index: 533429 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.1082. Min Act: -0.0000

Data Index: 628613 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0638. Min Act: -0.0000

Data Index: 1233041 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1339800 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0886. Min Act: -0.0000

Data Index: 634564 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.1190. Min Act: -0.0000

Data Index: 349047 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0466. Min Act: -0.0000

Data Index: 2992 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0724. Min Act: -0.0000

Data Index: 1148744 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0731. Min Act: -0.0000

Data Index: 302962 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1004308 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1246898 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0583. Min Act: -0.0000

Data Index: 1103270 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0587. Min Act: -0.0000

Data Index: 639747 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1213545 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0571. Min Act: -0.0000

Data Index: 825606 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0805. Min Act: -0.0000

Data Index: 147960 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0060. Min Act: -0.0000

Data Index: 984131 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.2573. Min Range: -1.2573

Max Act: 1.0008. Min Act: -0.0000

Data Index: 95778 (C4 (Web Text))

Max Activating Token Index: 247