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

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

Neuron 3113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2940. Min Act: -0.0000

Data Index: 809089 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1258. Min Act: -0.0000

Data Index: 185857 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1078. Min Act: -0.0000

Data Index: 857188 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1100. Min Act: -0.0000

Data Index: 488179 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1105. Min Act: -0.0000

Data Index: 879600 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1049. Min Act: -0.0000

Data Index: 624197 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0969. Min Act: -0.0000

Data Index: 684357 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0961. Min Act: -0.0000

Data Index: 710030 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1209714 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0804. Min Act: -0.0000

Data Index: 531828 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0917. Min Act: -0.0000

Data Index: 726400 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0835. Min Act: -0.0000

Data Index: 798213 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0812. Min Act: -0.0000

Data Index: 892419 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1074962 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0764. Min Act: -0.0000

Data Index: 687870 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0782. Min Act: -0.0000

Data Index: 868859 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0721. Min Act: -0.0000

Data Index: 807722 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0773. Min Act: -0.0000

Data Index: 295329 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0729. Min Act: -0.0000

Data Index: 943776 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1190734 (C4 (Web Text))

Max Activating Token Index: 174