Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 982 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.1086. Min Act: -0.0002

Data Index: 71397 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1005928 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0828. Min Act: -0.0003

Data Index: 568532 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0782. Min Act: -0.0002

Data Index: 939594 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1242018 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0809. Min Act: -0.0003

Data Index: 1183398 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0816. Min Act: -0.0004

Data Index: 1313508 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0798. Min Act: -0.0004

Data Index: 1260878 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0784. Min Act: -0.0003

Data Index: 507127 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0753. Min Act: -0.0004

Data Index: 1060600 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0734. Min Act: -0.0002

Data Index: 267301 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0707. Min Act: -0.0003

Data Index: 748890 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0735. Min Act: -0.0003

Data Index: 1207271 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0720. Min Act: -0.0003

Data Index: 73386 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0727. Min Act: -0.0001

Data Index: 811908 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1293640 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0724. Min Act: -0.0002

Data Index: 429384 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0734. Min Act: -0.0002

Data Index: 222273 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1194292 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.1086. Min Range: -0.1086

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1356426 (C4 (Web Text))

Max Activating Token Index: 487