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

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

Neuron 3139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6504. Min Act: -0.0001

Data Index: 914189 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6075. Min Act: -0.0001

Data Index: 727000 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6495. Min Act: -0.0001

Data Index: 269085 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1246488 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6047. Min Act: -0.0001

Data Index: 136513 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6007. Min Act: -0.0001

Data Index: 364568 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5736. Min Act: -0.0001

Data Index: 920162 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5685. Min Act: -0.0001

Data Index: 186637 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5471. Min Act: -0.0001

Data Index: 885001 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5774. Min Act: -0.0001

Data Index: 1001472 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1304805 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5565. Min Act: -0.0001

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5663. Min Act: -0.0001

Data Index: 168788 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5761. Min Act: -0.0001

Data Index: 823933 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5532. Min Act: -0.0001

Data Index: 654370 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5556. Min Act: -0.0001

Data Index: 137597 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5558. Min Act: -0.0001

Data Index: 1057314 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1320190 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5275. Min Act: -0.0001

Data Index: 552570 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5458. Min Act: -0.0001

Data Index: 166641 (C4 (Web Text))

Max Activating Token Index: 363