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

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

Neuron 4568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2655. Min Range: -3.2655

Max Act: 3.2655. Min Act: -0.0000

Data Index: 1574365 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 3.2655. Min Range: -3.2655

Max Act: 2.0422. Min Act: -0.0000

Data Index: 658854 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 3.2655. Min Range: -3.2655

Max Act: 2.0498. Min Act: -0.0000

Data Index: 1067980 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.8708. Min Act: -0.0000

Data Index: 768281 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.8391. Min Act: -0.0000

Data Index: 1609167 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.6873. Min Act: -0.0000

Data Index: 588000 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.8164. Min Act: -0.0000

Data Index: 745719 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1492813 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.6491. Min Act: -0.0000

Data Index: 188874 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1460666 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.5416. Min Act: -0.0000

Data Index: 105753 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.5373. Min Act: -0.0000

Data Index: 507814 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.4622. Min Act: -0.0000

Data Index: 99251 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.3814. Min Act: -0.0000

Data Index: 539048 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.3814. Min Act: -0.0000

Data Index: 494824 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.3621. Min Act: -0.0000

Data Index: 919395 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.5006. Min Act: -0.0000

Data Index: 834101 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.4018. Min Act: -0.0000

Data Index: 329905 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.4676. Min Act: -0.0000

Data Index: 1482112 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 3.2655. Min Range: -3.2655

Max Act: 1.4667. Min Act: -0.0000

Data Index: 964246 (C4 (Web Text))

Max Activating Token Index: 563