Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2727 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 142457 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1001. Min Act: -0.0001

Data Index: 274643 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0989. Min Act: -0.0001

Data Index: 214138 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0849. Min Act: -0.0001

Data Index: 517888 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1337000 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0958. Min Act: -0.0001

Data Index: 14690 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0834. Min Act: -0.0001

Data Index: 87623 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0694. Min Act: -0.0001

Data Index: 176517 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0852. Min Act: -0.0001

Data Index: 286279 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0760. Min Act: -0.0001

Data Index: 240990 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1307928 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0775. Min Act: -0.0001

Data Index: 172410 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0827. Min Act: -0.0001

Data Index: 888832 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0813. Min Act: -0.0001

Data Index: 672513 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1003578 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0838. Min Act: -0.0001

Data Index: 842194 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1232870 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0803. Min Act: -0.0001

Data Index: 231852 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0760. Min Act: -0.0001

Data Index: 674957 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0792. Min Act: -0.0001

Data Index: 49546 (C4 (Web Text))

Max Activating Token Index: 585