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

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

Neuron 5900 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: 1.2245. Min Range: -1.2245

Max Act: 1.2245. Min Act: -0.0002

Data Index: 1623454 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.2138. Min Act: -0.0002

Data Index: 1494933 (Python Code)

Max Activating Token Index: 304

Text #2

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.2192. Min Act: -0.0002

Data Index: 1647694 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.2046. Min Act: -0.0002

Data Index: 1618378 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1936. Min Act: -0.0002

Data Index: 1430272 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.2069. Min Act: -0.0002

Data Index: 1466857 (Python Code)

Max Activating Token Index: 533

Text #6

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1807. Min Act: -0.0002

Data Index: 1381561 (Python Code)

Max Activating Token Index: 697

Text #7

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1827. Min Act: -0.0002

Data Index: 1397968 (Python Code)

Max Activating Token Index: 427

Text #8

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1603. Min Act: -0.0002

Data Index: 1501221 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1672. Min Act: -0.0002

Data Index: 1608780 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1655. Min Act: -0.0002

Data Index: 1542411 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1448. Min Act: -0.0002

Data Index: 1586104 (Python Code)

Max Activating Token Index: 989

Text #12

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1555. Min Act: -0.0002

Data Index: 1651498 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1638. Min Act: -0.0002

Data Index: 1618824 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1472. Min Act: -0.0002

Data Index: 1620649 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1593. Min Act: -0.0002

Data Index: 1552353 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1386. Min Act: -0.0002

Data Index: 1626435 (Python Code)

Max Activating Token Index: 701

Text #17

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1228. Min Act: -0.0002

Data Index: 1435058 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1136. Min Act: -0.0002

Data Index: 1613211 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 1.2245. Min Range: -1.2245

Max Act: 1.1145. Min Act: -0.0002

Data Index: 1623568 (Python Code)

Max Activating Token Index: 294