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

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

Neuron 3772 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: 1.0247. Min Range: -1.0247

Max Act: 1.0247. Min Act: -0.0002

Data Index: 1360469 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9410. Min Act: -0.0002

Data Index: 1437401 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9242. Min Act: -0.0002

Data Index: 1559637 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9194. Min Act: -0.0002

Data Index: 1468660 (Python Code)

Max Activating Token Index: 857

Text #4

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9225. Min Act: -0.0002

Data Index: 1457243 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.9009. Min Act: -0.0002

Data Index: 1574090 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8804. Min Act: -0.0002

Data Index: 1649652 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8723. Min Act: -0.0002

Data Index: 1469975 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8887. Min Act: -0.0002

Data Index: 1459456 (Python Code)

Max Activating Token Index: 114

Text #9

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8633. Min Act: -0.0002

Data Index: 1567727 (Python Code)

Max Activating Token Index: 841

Text #10

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8532. Min Act: -0.0002

Data Index: 1405851 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8525. Min Act: -0.0002

Data Index: 1644092 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8437. Min Act: -0.0002

Data Index: 1503181 (Python Code)

Max Activating Token Index: 925

Text #13

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8347. Min Act: -0.0002

Data Index: 1600801 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8377. Min Act: -0.0002

Data Index: 1619555 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8271. Min Act: -0.0002

Data Index: 1594192 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8177. Min Act: -0.0002

Data Index: 1606334 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.8013. Min Act: -0.0002

Data Index: 1602230 (Python Code)

Max Activating Token Index: 811

Text #18

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7981. Min Act: -0.0002

Data Index: 1393294 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 1.0247. Min Range: -1.0247

Max Act: 0.7968. Min Act: -0.0002

Data Index: 1426307 (Python Code)

Max Activating Token Index: 302