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

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

Neuron 2160 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: 0.2060. Min Range: -0.2060

Max Act: 0.2060. Min Act: -0.0002

Data Index: 1202523 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1097306 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1243. Min Act: -0.0001

Data Index: 836919 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1199996 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1139. Min Act: -0.0002

Data Index: 930451 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1203654 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1091. Min Act: -0.0002

Data Index: 735772 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1098912 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.0811. Min Act: -0.0002

Data Index: 372174 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.0951. Min Act: -0.0001

Data Index: 725817 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1023. Min Act: -0.0002

Data Index: 739229 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.0987. Min Act: -0.0001

Data Index: 310584 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1011. Min Act: -0.0002

Data Index: 960392 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1119. Min Act: -0.0002

Data Index: 707516 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1020. Min Act: -0.0002

Data Index: 470267 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1008. Min Act: -0.0001

Data Index: 687407 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.0974. Min Act: -0.0002

Data Index: 858301 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.1077. Min Act: -0.0002

Data Index: 59260 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.0928. Min Act: -0.0001

Data Index: 217269 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.2060. Min Range: -0.2060

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1341741 (C4 (Web Text))

Max Activating Token Index: 158