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

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

Neuron 936 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1367. Min Act: -0.0003

Data Index: 856778 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1222. Min Act: -0.0002

Data Index: 962475 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1170. Min Act: -0.0002

Data Index: 111825 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1166. Min Act: -0.0002

Data Index: 996439 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1127. Min Act: -0.0002

Data Index: 156223 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1087. Min Act: -0.0002

Data Index: 928346 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1045370 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.1007. Min Act: -0.0002

Data Index: 191212 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1149219 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0996. Min Act: -0.0002

Data Index: 469451 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1288847 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0906. Min Act: -0.0002

Data Index: 206517 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1005919 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0871. Min Act: -0.0002

Data Index: 822375 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1028735 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1017925 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0834. Min Act: -0.0003

Data Index: 731892 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0830. Min Act: -0.0002

Data Index: 918280 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0828. Min Act: -0.0002

Data Index: 968724 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.1367. Min Range: -0.1367

Max Act: 0.0826. Min Act: -0.0002

Data Index: 959574 (C4 (Web Text))

Max Activating Token Index: 207