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

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

Neuron 2908 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: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0001

Data Index: 941997 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7529. Min Act: -0.0001

Data Index: 124600 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8394. Min Act: -0.0001

Data Index: 533152 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8297. Min Act: -0.0001

Data Index: 481009 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7844. Min Act: -0.0001

Data Index: 136273 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7099. Min Act: -0.0001

Data Index: 319926 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7530. Min Act: -0.0001

Data Index: 798576 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7734. Min Act: -0.0001

Data Index: 1213946 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1340890 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7008. Min Act: -0.0001

Data Index: 747434 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7234. Min Act: -0.0001

Data Index: 99557 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7137. Min Act: -0.0001

Data Index: 659929 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7188. Min Act: -0.0001

Data Index: 790143 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6533. Min Act: -0.0001

Data Index: 1067234 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6839. Min Act: -0.0001

Data Index: 98081 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6185. Min Act: -0.0001

Data Index: 752215 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6977. Min Act: -0.0001

Data Index: 69896 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6071. Min Act: -0.0001

Data Index: 1070782 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6913. Min Act: -0.0001

Data Index: 1301508 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6814. Min Act: -0.0001

Data Index: 952277 (C4 (Web Text))

Max Activating Token Index: 857