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

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

Neuron 502 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: 1.3720. Min Range: -1.3720

Max Act: 1.3720. Min Act: -0.0001

Data Index: 1421554 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.2358. Min Act: -0.0001

Data Index: 1398877 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.1800. Min Act: -0.0001

Data Index: 1503131 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0907. Min Act: -0.0001

Data Index: 1589720 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0991. Min Act: -0.0001

Data Index: 1499111 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0825. Min Act: -0.0001

Data Index: 1453602 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0559. Min Act: -0.0001

Data Index: 1586412 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0310. Min Act: -0.0001

Data Index: 1415298 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1371136 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1412471 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 1.3720. Min Range: -1.3720

Max Act: 1.0169. Min Act: -0.0001

Data Index: 1618896 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9629. Min Act: -0.0001

Data Index: 1390844 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9580. Min Act: -0.0001

Data Index: 1531475 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1558154 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1553286 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1526247 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8955. Min Act: -0.0001

Data Index: 1421855 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1417790 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1432589 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3720. Min Range: -1.3720

Max Act: 0.8721. Min Act: -0.0001

Data Index: 1517991 (Python Code)

Max Activating Token Index: 1023