Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1885 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1155. Min Act: -0.0002

Data Index: 282778 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1357970 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1117. Min Act: -0.0002

Data Index: 324411 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1105. Min Act: -0.0002

Data Index: 439263 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1008884 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1096. Min Act: -0.0002

Data Index: 695833 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1294916 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1326129 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1256290 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0882. Min Act: -0.0002

Data Index: 754160 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1254471 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1022185 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1122770 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0996. Min Act: -0.0002

Data Index: 897109 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0991. Min Act: -0.0002

Data Index: 447565 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1016. Min Act: -0.0002

Data Index: 357885 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1032. Min Act: -0.0002

Data Index: 1000044 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1017. Min Act: -0.0002

Data Index: 453776 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1054. Min Act: -0.0002

Data Index: 907029 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1033. Min Act: -0.0002

Data Index: 794208 (C4 (Web Text))

Max Activating Token Index: 191