Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 228 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0001

Data Index: 579125 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0985. Min Act: -0.0001

Data Index: 317103 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0957. Min Act: -0.0001

Data Index: 31999 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1081473 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0950. Min Act: -0.0001

Data Index: 341432 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0943. Min Act: -0.0001

Data Index: 151919 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0819. Min Act: -0.0001

Data Index: 144998 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1021497 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1001190 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0906. Min Act: -0.0001

Data Index: 828207 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0901. Min Act: -0.0001

Data Index: 987501 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0854. Min Act: -0.0001

Data Index: 948504 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1299380 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0751. Min Act: -0.0001

Data Index: 426209 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0933. Min Act: -0.0001

Data Index: 643358 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0775. Min Act: -0.0001

Data Index: 943023 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1338597 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0834. Min Act: -0.0001

Data Index: 600676 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1327406 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0766. Min Act: -0.0001

Data Index: 183162 (C4 (Web Text))

Max Activating Token Index: 990