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

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

Neuron 3794 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: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0003

Data Index: 350396 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0562. Min Act: -0.0003

Data Index: 291352 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1252748 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1363013 (Python Code)

Max Activating Token Index: 94

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0564. Min Act: -0.0003

Data Index: 763561 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0549. Min Act: -0.0003

Data Index: 507320 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0542. Min Act: -0.0003

Data Index: 674417 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0523. Min Act: -0.0003

Data Index: 334344 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1257763 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0518. Min Act: -0.0003

Data Index: 749975 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0514. Min Act: -0.0002

Data Index: 291997 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1546528 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1473422 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0529. Min Act: -0.0003

Data Index: 401803 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1225800 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1208842 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0520. Min Act: -0.0003

Data Index: 939853 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0490. Min Act: -0.0003

Data Index: 766599 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1361245 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0484. Min Act: -0.0003

Data Index: 466313 (C4 (Web Text))

Max Activating Token Index: 900