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

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

Neuron 2865 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2746. Min Act: -0.0001

Data Index: 588911 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2196. Min Act: -0.0001

Data Index: 1588006 (Python Code)

Max Activating Token Index: 140

Text #2

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1192195 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2165. Min Act: -0.0001

Data Index: 1482231 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1140. Min Act: -0.0001

Data Index: 227723 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2010. Min Act: -0.0001

Data Index: 646243 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1550. Min Act: -0.0001

Data Index: 1285514 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1500. Min Act: -0.0001

Data Index: 109872 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1660. Min Act: -0.0001

Data Index: 1176073 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1105. Min Act: -0.0001

Data Index: 146023 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1439300 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.2155. Min Act: -0.0001

Data Index: 670390 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1067. Min Act: -0.0001

Data Index: 758405 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0792. Min Act: -0.0001

Data Index: 1129209 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0712. Min Act: -0.0001

Data Index: 461438 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1277. Min Act: -0.0001

Data Index: 1243923 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0866. Min Act: -0.0000

Data Index: 558665 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.1369. Min Act: -0.0001

Data Index: 258160 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0114. Min Act: -0.0001

Data Index: 1148049 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.2746. Min Range: -1.2746

Max Act: 1.0032. Min Act: -0.0001

Data Index: 561694 (C4 (Web Text))

Max Activating Token Index: 627