Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 528 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2173. Min Act: -0.0001

Data Index: 765611 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2207. Min Act: -0.0001

Data Index: 234229 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.0001

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1627. Min Act: -0.0001

Data Index: 696534 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1582. Min Act: -0.0001

Data Index: 513965 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1878. Min Act: -0.0001

Data Index: 1212077 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1240223 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1181587 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1623. Min Act: -0.0001

Data Index: 855461 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1598. Min Act: -0.0001

Data Index: 741242 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1200421 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1751. Min Act: -0.0001

Data Index: 78261 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1348712 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1298. Min Act: -0.0001

Data Index: 305903 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1128294 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1415. Min Act: -0.0001

Data Index: 26943 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1244046 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1593645 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1500. Min Act: -0.0001

Data Index: 96086 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1466. Min Act: -0.0001

Data Index: 61505 (C4 (Web Text))

Max Activating Token Index: 36