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

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

Neuron 5041 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.1469. Min Act: -0.0000

Data Index: 933681 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0947. Min Act: -0.0000

Data Index: 837981 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0932. Min Act: -0.0000

Data Index: 537188 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0693. Min Act: -0.0000

Data Index: 104502 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0632. Min Act: -0.0000

Data Index: 775962 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.7429. Min Act: -0.0000

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.1129. Min Act: -0.0000

Data Index: 59718 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.9057. Min Act: -0.0000

Data Index: 749327 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 3.1469. Min Range: -3.1469

Max Act: 3.0967. Min Act: -0.0000

Data Index: 714821 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.9493. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.7692. Min Act: -0.0000

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.7425. Min Act: -0.0000

Data Index: 1074533 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 3.1469. Min Range: -3.1469

Max Act: 2.6205. Min Act: -0.0000

Data Index: 940508 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.1469. Min Range: -3.1469

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1064930 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.1469. Min Range: -3.1469

Max Act: 0.8486. Min Act: -0.0000

Data Index: 80990 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 3.1469. Min Range: -3.1469

Max Act: 0.8482. Min Act: -0.0000

Data Index: 973863 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.1469. Min Range: -3.1469

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1263124 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.1469. Min Range: -3.1469

Max Act: 0.7830. Min Act: -0.0000

Data Index: 681564 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.1469. Min Range: -3.1469

Max Act: 0.7664. Min Act: -0.0000

Data Index: 768195 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.1469. Min Range: -3.1469

Max Act: 0.7473. Min Act: -0.0000

Data Index: 403895 (C4 (Web Text))

Max Activating Token Index: 939