Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1432 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1140. Min Act: -0.0003

Data Index: 946772 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1059. Min Act: -0.0004

Data Index: 387637 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.1031. Min Act: -0.0004

Data Index: 1111262 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0957. Min Act: -0.0003

Data Index: 915693 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0882. Min Act: -0.0004

Data Index: 1278252 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0873. Min Act: -0.0003

Data Index: 1101634 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0877. Min Act: -0.0003

Data Index: 1225228 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0858. Min Act: -0.0003

Data Index: 64995 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0828. Min Act: -0.0003

Data Index: 1023447 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0785. Min Act: -0.0002

Data Index: 842563 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0812. Min Act: -0.0003

Data Index: 1139133 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0814. Min Act: -0.0003

Data Index: 510122 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0828. Min Act: -0.0003

Data Index: 132599 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0830. Min Act: -0.0002

Data Index: 177058 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0812. Min Act: -0.0003

Data Index: 47784 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0810. Min Act: -0.0004

Data Index: 926237 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0827. Min Act: -0.0003

Data Index: 421519 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0803. Min Act: -0.0003

Data Index: 242826 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0791. Min Act: -0.0003

Data Index: 527632 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.1140. Min Range: -0.1140

Max Act: 0.0791. Min Act: -0.0002

Data Index: 341384 (C4 (Web Text))

Max Activating Token Index: 1005