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

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

Neuron 427 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1089600 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1230298 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0083. Min Act: -0.0006

Data Index: 290613 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0080. Min Act: -0.0006

Data Index: 777216 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0075. Min Act: -0.0006

Data Index: 570250 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0006

Data Index: 335649 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0079. Min Act: -0.0006

Data Index: 628088 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0006

Data Index: 682487 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1089328 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1322146 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0074. Min Act: -0.0006

Data Index: 156384 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1053526 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1276450 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0074. Min Act: -0.0006

Data Index: 106533 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0071. Min Act: -0.0006

Data Index: 182631 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0070. Min Act: -0.0006

Data Index: 766891 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0072. Min Act: -0.0006

Data Index: 14121 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0076. Min Act: -0.0006

Data Index: 773680 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0074. Min Act: -0.0006

Data Index: 295557 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0072. Min Act: -0.0006

Data Index: 856012 (C4 (Web Text))

Max Activating Token Index: 904