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

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

Neuron 1631 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2004. Min Range: -1.2004

Max Act: 1.2004. Min Act: -0.0000

Data Index: 609486 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.2004. Min Range: -1.2004

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1214825 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.2004. Min Range: -1.2004

Max Act: 1.0930. Min Act: -0.0000

Data Index: 33461 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.9913. Min Act: -0.0000

Data Index: 691117 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8065. Min Act: -0.0000

Data Index: 781217 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8530. Min Act: -0.0000

Data Index: 842170 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1019075 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8225. Min Act: -0.0000

Data Index: 163856 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1468567 (Python Code)

Max Activating Token Index: 622

Text #9

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1487862 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1196967 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7659. Min Act: -0.0000

Data Index: 668015 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1534156 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7692. Min Act: -0.0000

Data Index: 849222 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6838. Min Act: -0.0000

Data Index: 634116 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1551719 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1497479 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7065. Min Act: -0.0000

Data Index: 193651 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1190873 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.2004. Min Range: -1.2004

Max Act: 0.7104. Min Act: -0.0000

Data Index: 1516660 (Python Code)

Max Activating Token Index: 749