Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2231 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1502. Min Act: -0.0004

Data Index: 1416869 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1500. Min Act: -0.0004

Data Index: 1620772 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1368. Min Act: -0.0004

Data Index: 1627415 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1231. Min Act: -0.0004

Data Index: 1490523 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1187. Min Act: -0.0004

Data Index: 1472590 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1218. Min Act: -0.0004

Data Index: 1510306 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1114. Min Act: -0.0004

Data Index: 1540257 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1048. Min Act: -0.0004

Data Index: 1470006 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1071. Min Act: -0.0004

Data Index: 1372236 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0985. Min Act: -0.0004

Data Index: 1542128 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1002. Min Act: -0.0004

Data Index: 1453737 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0931. Min Act: -0.0004

Data Index: 1608557 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0944. Min Act: -0.0004

Data Index: 1560043 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0946. Min Act: -0.0004

Data Index: 1577461 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0865. Min Act: -0.0004

Data Index: 1589766 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0850. Min Act: -0.0004

Data Index: 1429998 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0844. Min Act: -0.0004

Data Index: 1422926 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0865. Min Act: -0.0004

Data Index: 1369244 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0830. Min Act: -0.0004

Data Index: 1519616 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0894. Min Act: -0.0004

Data Index: 1455810 (Python Code)

Max Activating Token Index: 1023