Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3828 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0874. Min Act: -0.0001

Data Index: 1115673 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1327512 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1269229 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0814. Min Act: -0.0001

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0713. Min Act: -0.0001

Data Index: 701681 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0738. Min Act: -0.0001

Data Index: 1834 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0749. Min Act: -0.0001

Data Index: 108393 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0735. Min Act: -0.0001

Data Index: 774576 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1136441 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0675. Min Act: -0.0001

Data Index: 954052 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0645. Min Act: -0.0001

Data Index: 860731 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0716. Min Act: -0.0001

Data Index: 952339 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1095089 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0692. Min Act: -0.0001

Data Index: 250282 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1068241 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0637. Min Act: -0.0001

Data Index: 350517 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0696. Min Act: -0.0001

Data Index: 35167 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0632. Min Act: -0.0001

Data Index: 752303 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0688. Min Act: -0.0001

Data Index: 1306512 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0680. Min Act: -0.0001

Data Index: 975214 (C4 (Web Text))

Max Activating Token Index: 45