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

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

Neuron 1860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6780. Min Act: -0.0002

Data Index: 350589 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5654. Min Act: -0.0002

Data Index: 511292 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5745. Min Act: -0.0002

Data Index: 539327 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5373. Min Act: -0.0002

Data Index: 159053 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5753. Min Act: -0.0002

Data Index: 728408 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5513. Min Act: -0.0002

Data Index: 551873 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4949. Min Act: -0.0002

Data Index: 1277612 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4848. Min Act: -0.0002

Data Index: 358166 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5052. Min Act: -0.0002

Data Index: 983722 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4446. Min Act: -0.0002

Data Index: 59682 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5087. Min Act: -0.0002

Data Index: 152960 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4900. Min Act: -0.0002

Data Index: 960785 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4672. Min Act: -0.0002

Data Index: 1107738 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4411. Min Act: -0.0002

Data Index: 1039188 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4792. Min Act: -0.0002

Data Index: 181101 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4314. Min Act: -0.0002

Data Index: 1085951 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5032. Min Act: -0.0002

Data Index: 187247 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4284. Min Act: -0.0002

Data Index: 337733 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4484. Min Act: -0.0002

Data Index: 1333156 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4773. Min Act: -0.0002

Data Index: 720538 (C4 (Web Text))

Max Activating Token Index: 502