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

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

Neuron 166 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1064. Min Act: -0.0001

Data Index: 578669 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1048. Min Act: -0.0001

Data Index: 119527 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0001

Data Index: 569418 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1481121 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1604743 (Python Code)

Max Activating Token Index: 125

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1407021 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0983. Min Act: -0.0001

Data Index: 31572 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1488250 (Python Code)

Max Activating Token Index: 534

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1553392 (Python Code)

Max Activating Token Index: 544

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1398018 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1366670 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1647415 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0929. Min Act: -0.0001

Data Index: 73920 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1417980 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0933. Min Act: -0.0001

Data Index: 66078 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1436286 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1422991 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0882. Min Act: -0.0001

Data Index: 362500 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1508422 (Python Code)

Max Activating Token Index: 498

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1614889 (Python Code)

Max Activating Token Index: 256