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

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

Neuron 1612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1544454 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1118589 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1407616 (Python Code)

Max Activating Token Index: 187

Text #3

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1374449 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1233. Min Act: -0.0001

Data Index: 953051 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1062. Min Act: -0.0001

Data Index: 652900 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1118. Min Act: -0.0001

Data Index: 464692 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1008. Min Act: -0.0001

Data Index: 775514 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1266668 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1595052 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1244786 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1243916 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1012152 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1045. Min Act: -0.0001

Data Index: 477742 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1005. Min Act: -0.0001

Data Index: 774810 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1080. Min Act: -0.0001

Data Index: 617122 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1266510 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1096626 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.1156. Min Act: -0.0001

Data Index: 731943 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.1389. Min Range: -0.1389

Max Act: 0.0956. Min Act: -0.0001

Data Index: 62719 (C4 (Web Text))

Max Activating Token Index: 191