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

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

Neuron 1619 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1146. Min Act: -0.0002

Data Index: 419386 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1110. Min Act: -0.0002

Data Index: 75895 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1092. Min Act: -0.0002

Data Index: 238181 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1081. Min Act: -0.0002

Data Index: 673207 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0002

Data Index: 486454 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1020. Min Act: -0.0002

Data Index: 201115 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1015011 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1171739 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1347018 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1121724 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1143148 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0913. Min Act: -0.0002

Data Index: 90173 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0872. Min Act: -0.0002

Data Index: 896887 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0897. Min Act: -0.0002

Data Index: 107643 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0919. Min Act: -0.0002

Data Index: 117511 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0879. Min Act: -0.0002

Data Index: 496011 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0807. Min Act: -0.0002

Data Index: 933017 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1008339 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0871. Min Act: -0.0002

Data Index: 429704 (C4 (Web Text))

Max Activating Token Index: 48