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

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

Neuron 5845 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1308. Min Act: 0.0000

Data Index: 605876 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1170. Min Act: -0.0000

Data Index: 650228 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1255. Min Act: 0.0000

Data Index: 1086834 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1127. Min Act: -0.0000

Data Index: 909392 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1076. Min Act: -0.0000

Data Index: 356133 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1050. Min Act: -0.0000

Data Index: 373946 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1167835 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0952. Min Act: 0.0000

Data Index: 1011023 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.1009. Min Act: -0.0000

Data Index: 208230 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1359350 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1250595 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0879. Min Act: 0.0000

Data Index: 723039 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1087215 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1256139 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0899. Min Act: 0.0000

Data Index: 31390 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1141879 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0845. Min Act: -0.0000

Data Index: 108804 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1001719 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0834. Min Act: -0.0000

Data Index: 643606 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1308. Min Range: -0.1308

Max Act: 0.0795. Min Act: 0.0000

Data Index: 889172 (C4 (Web Text))

Max Activating Token Index: 747