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

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

Neuron 3872 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: 0.9799. Min Range: -0.9799

Max Act: 0.9799. Min Act: -0.0002

Data Index: 1560979 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9528. Min Act: -0.0002

Data Index: 1464562 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9260. Min Act: -0.0002

Data Index: 1644636 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.9216. Min Act: -0.0002

Data Index: 1528234 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8943. Min Act: -0.0002

Data Index: 1643433 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8848. Min Act: -0.0002

Data Index: 1611342 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8714. Min Act: -0.0002

Data Index: 1586622 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8753. Min Act: -0.0002

Data Index: 1577602 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8660. Min Act: -0.0002

Data Index: 1628737 (Python Code)

Max Activating Token Index: 452

Text #9

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8779. Min Act: -0.0002

Data Index: 1492801 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8851. Min Act: -0.0002

Data Index: 1416333 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8639. Min Act: -0.0002

Data Index: 1392650 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8580. Min Act: -0.0002

Data Index: 1443681 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8692. Min Act: -0.0002

Data Index: 1399026 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8769. Min Act: -0.0002

Data Index: 1438185 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8460. Min Act: -0.0002

Data Index: 1432105 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8439. Min Act: -0.0002

Data Index: 1495172 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8437. Min Act: -0.0002

Data Index: 1630089 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8487. Min Act: -0.0002

Data Index: 1617835 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.9799. Min Range: -0.9799

Max Act: 0.8377. Min Act: -0.0002

Data Index: 1370707 (Python Code)

Max Activating Token Index: 61