Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 416 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: -0.0003

Data Index: 424711 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1043. Min Act: -0.0003

Data Index: 1342795 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0857. Min Act: -0.0004

Data Index: 669736 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1147240 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0859. Min Act: -0.0003

Data Index: 1041366 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0915. Min Act: -0.0003

Data Index: 116728 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0907. Min Act: -0.0003

Data Index: 1274586 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0923. Min Act: -0.0003

Data Index: 764493 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0792. Min Act: -0.0003

Data Index: 202162 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0795. Min Act: -0.0003

Data Index: 371836 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0881. Min Act: -0.0003

Data Index: 280124 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1327884 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0733. Min Act: -0.0003

Data Index: 122445 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0822. Min Act: -0.0004

Data Index: 609336 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0846. Min Act: -0.0003

Data Index: 1001039 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0790. Min Act: -0.0003

Data Index: 433193 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0816. Min Act: -0.0004

Data Index: 1311899 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0845. Min Act: -0.0003

Data Index: 1126800 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0841. Min Act: -0.0003

Data Index: 213293 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0834. Min Act: -0.0003

Data Index: 5432 (C4 (Web Text))

Max Activating Token Index: 476