Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1529 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1080. Min Act: -0.0003

Data Index: 571145 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1075. Min Act: -0.0003

Data Index: 923905 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1070. Min Act: -0.0003

Data Index: 496090 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1083. Min Act: -0.0003

Data Index: 1274151 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1016. Min Act: -0.0003

Data Index: 283961 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1025. Min Act: -0.0003

Data Index: 917497 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1011902 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1020. Min Act: -0.0003

Data Index: 1158251 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1019. Min Act: -0.0003

Data Index: 133685 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1015. Min Act: -0.0003

Data Index: 817487 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1011. Min Act: -0.0002

Data Index: 816231 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1008. Min Act: -0.0003

Data Index: 677544 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1241268 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0960. Min Act: -0.0002

Data Index: 1350537 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0971. Min Act: -0.0003

Data Index: 977584 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0963. Min Act: -0.0001

Data Index: 701743 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0969. Min Act: -0.0003

Data Index: 506911 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0935. Min Act: -0.0003

Data Index: 83955 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1107053 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0930. Min Act: -0.0003

Data Index: 127322 (C4 (Web Text))

Max Activating Token Index: 315