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

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

Neuron 237 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1093474 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.8893. Min Act: -0.0000

Data Index: 832884 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.9360. Min Act: -0.0000

Data Index: 518271 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7829. Min Act: -0.0000

Data Index: 44443 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7290. Min Act: -0.0000

Data Index: 144874 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1167960 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1307353 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7576. Min Act: -0.0000

Data Index: 695251 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.5749. Min Act: -0.0000

Data Index: 927327 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6841. Min Act: -0.0000

Data Index: 275490 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6430. Min Act: -0.0000

Data Index: 658445 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6842. Min Act: -0.0000

Data Index: 84106 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6576. Min Act: -0.0000

Data Index: 850757 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.7100. Min Act: -0.0000

Data Index: 553910 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1161773 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6432. Min Act: -0.0000

Data Index: 163692 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1095641 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6386. Min Act: -0.0000

Data Index: 845331 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.5818. Min Act: -0.0000

Data Index: 172713 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.9360. Min Range: -0.9360

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1260852 (C4 (Web Text))

Max Activating Token Index: 579