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

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

Neuron 1569 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0005

Data Index: 1028304 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1041837 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0101. Min Act: -0.0006

Data Index: 3565 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0006

Data Index: 777470 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0005

Data Index: 884092 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0006

Data Index: 830573 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0095. Min Act: -0.0005

Data Index: 1307708 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0006

Data Index: 17314 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0095. Min Act: -0.0005

Data Index: 29370 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0005

Data Index: 373637 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0094. Min Act: -0.0006

Data Index: 3732 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0094. Min Act: -0.0006

Data Index: 244564 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1349589 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1073268 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0094. Min Act: -0.0005

Data Index: 129772 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0094. Min Act: -0.0005

Data Index: 18309 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1064642 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0006

Data Index: 280787 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0006

Data Index: 192829 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0092. Min Act: -0.0005

Data Index: 839734 (C4 (Web Text))

Max Activating Token Index: 392