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

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

Neuron 1245 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 635515 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1205. Min Act: -0.0001

Data Index: 177785 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1159. Min Act: -0.0001

Data Index: 368200 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1303226 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0940. Min Act: -0.0001

Data Index: 830124 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1245454 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1496041 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0806. Min Act: -0.0001

Data Index: 86529 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0887. Min Act: -0.0001

Data Index: 413769 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0868. Min Act: -0.0001

Data Index: 11333 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0779. Min Act: -0.0001

Data Index: 949408 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0835. Min Act: -0.0001

Data Index: 243890 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0823. Min Act: -0.0001

Data Index: 167915 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1304906 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1190624 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0750. Min Act: -0.0001

Data Index: 27187 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1492645 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1194408 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0815. Min Act: -0.0001

Data Index: 128419 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1207726 (C4 (Web Text))

Max Activating Token Index: 510