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

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

Neuron 3324 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.3852. Min Act: -0.0002

Data Index: 1457660 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.1536. Min Act: -0.0002

Data Index: 1589063 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.0267. Min Act: -0.0002

Data Index: 1405667 (Python Code)

Max Activating Token Index: 501

Text #3

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.0054. Min Act: -0.0002

Data Index: 1562213 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.0134. Min Act: -0.0002

Data Index: 1484264 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 1.3852. Min Range: -1.3852

Max Act: 1.0058. Min Act: -0.0002

Data Index: 1627686 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9944. Min Act: -0.0002

Data Index: 1373928 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9749. Min Act: -0.0002

Data Index: 1401964 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9633. Min Act: -0.0002

Data Index: 1572936 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9531. Min Act: -0.0002

Data Index: 1499878 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9649. Min Act: -0.0002

Data Index: 1420010 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9478. Min Act: -0.0002

Data Index: 1395372 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9359. Min Act: -0.0002

Data Index: 1458081 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9447. Min Act: -0.0002

Data Index: 1382576 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9543. Min Act: -0.0002

Data Index: 1365571 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9361. Min Act: -0.0002

Data Index: 1367150 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9344. Min Act: -0.0002

Data Index: 1501173 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9302. Min Act: -0.0002

Data Index: 1642803 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9362. Min Act: -0.0002

Data Index: 1461980 (Python Code)

Max Activating Token Index: 931

Text #19

Max Range: 1.3852. Min Range: -1.3852

Max Act: 0.9142. Min Act: -0.0002

Data Index: 1633238 (Python Code)

Max Activating Token Index: 594