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

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

Neuron 3217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1133375 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.8066. Min Act: -0.0000

Data Index: 828853 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7235. Min Act: -0.0000

Data Index: 682414 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.7585. Min Act: -0.0000

Data Index: 761425 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6634. Min Act: -0.0000

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6515. Min Act: -0.0000

Data Index: 160786 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6732. Min Act: -0.0000

Data Index: 98259 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6505. Min Act: -0.0000

Data Index: 536552 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6268. Min Act: -0.0000

Data Index: 566188 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1105491 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6010. Min Act: -0.0000

Data Index: 603400 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1094407 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6405. Min Act: -0.0000

Data Index: 700295 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6343. Min Act: -0.0000

Data Index: 986899 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1172741 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5459. Min Act: -0.0000

Data Index: 272962 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6647. Min Act: -0.0000

Data Index: 618577 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5884. Min Act: -0.0000

Data Index: 767009 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.5894. Min Act: -0.0000

Data Index: 130261 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.8066. Min Range: -0.8066

Max Act: 0.6078. Min Act: -0.0000

Data Index: 633697 (C4 (Web Text))

Max Activating Token Index: 315