Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5586 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.3026. Min Act: 0.0000

Data Index: 1331015 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.3722. Min Act: -0.0000

Data Index: 686245 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1134137 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.3572. Min Act: -0.0000

Data Index: 317405 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.2592. Min Act: -0.0000

Data Index: 867655 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.2819. Min Act: -0.0000

Data Index: 784131 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.2264. Min Act: -0.0000

Data Index: 707948 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.2252. Min Act: -0.0000

Data Index: 360144 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1831. Min Act: -0.0000

Data Index: 171699 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0751. Min Act: -0.0000

Data Index: 182171 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1103621 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1315861 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1159. Min Act: -0.0000

Data Index: 723776 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1473. Min Act: -0.0000

Data Index: 683769 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0271. Min Act: -0.0000

Data Index: 1389499 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1181066 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1103734 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1058. Min Act: -0.0000

Data Index: 849615 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0857. Min Act: -0.0000

Data Index: 327435 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0330. Min Act: -0.0000

Data Index: 671286 (C4 (Web Text))

Max Activating Token Index: 176