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

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

Neuron 49 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: 0.1118. Min Range: -0.1118

Max Act: 0.1118. Min Act: -0.0003

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1039. Min Act: -0.0002

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1047. Min Act: -0.0003

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1022. Min Act: -0.0003

Data Index: 645215 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1042. Min Act: -0.0003

Data Index: 346515 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0959. Min Act: -0.0002

Data Index: 820793 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.1009. Min Act: -0.0003

Data Index: 774473 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0949. Min Act: -0.0003

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0940. Min Act: -0.0003

Data Index: 875650 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1054954 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0937. Min Act: -0.0002

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0948. Min Act: -0.0003

Data Index: 816696 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0886. Min Act: -0.0002

Data Index: 196487 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0876. Min Act: -0.0003

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0870. Min Act: -0.0003

Data Index: 801071 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0885. Min Act: -0.0003

Data Index: 848017 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0867. Min Act: -0.0003

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0910. Min Act: -0.0004

Data Index: 257106 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0843. Min Act: -0.0004

Data Index: 1044631 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.1118. Min Range: -0.1118

Max Act: 0.0850. Min Act: -0.0002

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 734