Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 167 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1110794 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1035932 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1166. Min Act: -0.0001

Data Index: 128802 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1195. Min Act: -0.0002

Data Index: 1248148 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1599415 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1115. Min Act: -0.0002

Data Index: 656068 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1125. Min Act: -0.0002

Data Index: 998601 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1073. Min Act: -0.0001

Data Index: 865086 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1478734 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1068. Min Act: -0.0002

Data Index: 117167 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1656649 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1365545 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1500534 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1339348 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1067. Min Act: -0.0001

Data Index: 415144 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1027. Min Act: -0.0001

Data Index: 475384 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1576470 (Python Code)

Max Activating Token Index: 233

Text #17

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1047. Min Act: -0.0002

Data Index: 816662 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1604616 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1321214 (C4 (Web Text))

Max Activating Token Index: 342