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

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

Neuron 1725 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: 0.1079. Min Range: -0.1079

Max Act: 0.0905. Min Act: -0.0002

Data Index: 353570 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0993. Min Act: -0.0002

Data Index: 291938 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1079. Min Act: -0.0002

Data Index: 168949 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1130040 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1217590 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0896. Min Act: -0.0002

Data Index: 616447 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0851. Min Act: -0.0002

Data Index: 195913 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0840. Min Act: -0.0002

Data Index: 432569 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0859. Min Act: -0.0002

Data Index: 309732 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0870. Min Act: -0.0002

Data Index: 75189 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1314127 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1174509 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0879. Min Act: -0.0002

Data Index: 454609 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1171545 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.1039. Min Act: -0.0002

Data Index: 997408 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0834. Min Act: -0.0002

Data Index: 572905 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0749. Min Act: -0.0002

Data Index: 536745 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1138623 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0786. Min Act: -0.0002

Data Index: 95603 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1345471 (C4 (Web Text))

Max Activating Token Index: 533