Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5030 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1595625 (Python Code)

Max Activating Token Index: 606

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1518453 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1640335 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1492456 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1584903 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1399894 (Python Code)

Max Activating Token Index: 937

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1485907 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1494411 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1507429 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1462794 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1605819 (Python Code)

Max Activating Token Index: 672

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1369607 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1559683 (Python Code)

Max Activating Token Index: 247

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1050. Min Act: -0.0000

Data Index: 201063 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1370467 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1488247 (Python Code)

Max Activating Token Index: 977

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1403804 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1519992 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1405393 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1546049 (Python Code)

Max Activating Token Index: 1018