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

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

Neuron 3564 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7640. Min Act: -0.0002

Data Index: 739072 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7732. Min Act: -0.0002

Data Index: 321233 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.7087. Min Act: -0.0002

Data Index: 416882 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5679. Min Act: -0.0002

Data Index: 104268 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5845. Min Act: -0.0002

Data Index: 1348395 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5709. Min Act: -0.0002

Data Index: 638397 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5882. Min Act: -0.0002

Data Index: 83870 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5421. Min Act: -0.0003

Data Index: 1076197 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5241. Min Act: -0.0002

Data Index: 1185732 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4925. Min Act: -0.0002

Data Index: 176634 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.5175. Min Act: -0.0003

Data Index: 493423 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4724. Min Act: -0.0002

Data Index: 785443 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4925. Min Act: -0.0002

Data Index: 1343131 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4908. Min Act: -0.0002

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4746. Min Act: -0.0002

Data Index: 1298930 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4803. Min Act: -0.0002

Data Index: 118394 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4745. Min Act: -0.0002

Data Index: 606245 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4445. Min Act: -0.0002

Data Index: 1144675 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4423. Min Act: -0.0002

Data Index: 313301 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.7732. Min Range: -0.7732

Max Act: 0.4278. Min Act: -0.0003

Data Index: 1315575 (C4 (Web Text))

Max Activating Token Index: 102