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

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

Neuron 3041 in Layer 0

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: 0.7274. Min Range: -0.7274

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1579107 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6289. Min Act: -0.0001

Data Index: 1527246 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1495096 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6157. Min Act: -0.0001

Data Index: 1460763 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1629734 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5969. Min Act: -0.0001

Data Index: 1404887 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1368623 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5934. Min Act: -0.0001

Data Index: 1469527 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.6073. Min Act: -0.0001

Data Index: 1478774 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1638245 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5819. Min Act: -0.0002

Data Index: 1474539 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5901. Min Act: -0.0001

Data Index: 1523228 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1479893 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5825. Min Act: -0.0001

Data Index: 1508216 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5709. Min Act: -0.0001

Data Index: 1381453 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5674. Min Act: -0.0001

Data Index: 948063 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5723. Min Act: -0.0001

Data Index: 1491076 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5672. Min Act: -0.0001

Data Index: 1365674 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5660. Min Act: -0.0001

Data Index: 1503880 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.7274. Min Range: -0.7274

Max Act: 0.5609. Min Act: -0.0001

Data Index: 1541236 (Python Code)

Max Activating Token Index: 1023