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

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

Neuron 1355 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.7896. Min Act: -0.0000

Data Index: 1240659 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1422413 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.4307. Min Act: -0.0000

Data Index: 366294 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.2965. Min Act: -0.0000

Data Index: 1443462 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.2076. Min Act: -0.0000

Data Index: 1299413 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.2029. Min Act: -0.0000

Data Index: 1565283 (Python Code)

Max Activating Token Index: 677

Text #6

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.1442. Min Act: -0.0000

Data Index: 1470719 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.0903. Min Act: -0.0000

Data Index: 1655316 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9591. Min Act: -0.0000

Data Index: 1610880 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9634. Min Act: -0.0000

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.0079. Min Act: -0.0000

Data Index: 831660 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1380303 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.0059. Min Act: -0.0000

Data Index: 38874 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9847. Min Act: -0.0000

Data Index: 1054312 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9836. Min Act: -0.0000

Data Index: 644463 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.8669. Min Act: -0.0000

Data Index: 1236942 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9811. Min Act: -0.0000

Data Index: 1322209 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9801. Min Act: -0.0000

Data Index: 472649 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 2.7896. Min Range: -2.7896

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1445662 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 2.7896. Min Range: -2.7896

Max Act: 1.9595. Min Act: -0.0000

Data Index: 865519 (C4 (Web Text))

Max Activating Token Index: 331