Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2625 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0210. Min Range: -1.0210

Max Act: 1.0210. Min Act: -0.0001

Data Index: 1634829 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8797. Min Act: -0.0001

Data Index: 1367553 (Python Code)

Max Activating Token Index: 835

Text #2

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7911. Min Act: -0.0001

Data Index: 1630049 (Python Code)

Max Activating Token Index: 599

Text #3

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8551. Min Act: -0.0001

Data Index: 601163 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7911. Min Act: -0.0001

Data Index: 1392023 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1521902 (Python Code)

Max Activating Token Index: 589

Text #6

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8295. Min Act: -0.0001

Data Index: 1410508 (Python Code)

Max Activating Token Index: 801

Text #7

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1548653 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8011. Min Act: -0.0001

Data Index: 1555975 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1457885 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8340. Min Act: -0.0001

Data Index: 1649295 (Python Code)

Max Activating Token Index: 754

Text #11

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1506374 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1448737 (Python Code)

Max Activating Token Index: 742

Text #13

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8112. Min Act: -0.0001

Data Index: 1614529 (Python Code)

Max Activating Token Index: 711

Text #14

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1483592 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7390. Min Act: -0.0001

Data Index: 1528504 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7842. Min Act: -0.0001

Data Index: 1383766 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1633194 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7261. Min Act: -0.0001

Data Index: 1654175 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 1.0210. Min Range: -1.0210

Max Act: 0.7472. Min Act: -0.0001

Data Index: 277968 (C4 (Web Text))

Max Activating Token Index: 18