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

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

Neuron 1757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1137. Min Act: -0.0001

Data Index: 872081 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1042242 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1016427 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1082766 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1168504 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1083. Min Act: -0.0001

Data Index: 490794 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1262149 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1331927 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1087555 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1287672 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1334804 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1011. Min Act: -0.0001

Data Index: 97737 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0913. Min Act: -0.0001

Data Index: 52432 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0983. Min Act: -0.0001

Data Index: 690991 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0987. Min Act: -0.0001

Data Index: 989795 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0968. Min Act: -0.0001

Data Index: 641354 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0964. Min Act: -0.0001

Data Index: 1235485 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1271865 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0985. Min Act: -0.0001

Data Index: 401239 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0911. Min Act: -0.0001

Data Index: 399015 (C4 (Web Text))

Max Activating Token Index: 494