Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1482 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0612. Min Act: -0.0003

Data Index: 111843 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0597. Min Act: -0.0003

Data Index: 527856 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0576. Min Act: -0.0003

Data Index: 373843 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0555. Min Act: -0.0003

Data Index: 447214 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0535. Min Act: -0.0003

Data Index: 610179 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0536. Min Act: -0.0003

Data Index: 547504 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0542. Min Act: -0.0004

Data Index: 130069 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0528. Min Act: -0.0003

Data Index: 921684 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0521. Min Act: -0.0003

Data Index: 877134 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0516. Min Act: -0.0003

Data Index: 59214 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1125997 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0491. Min Act: -0.0003

Data Index: 244562 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0485. Min Act: -0.0003

Data Index: 628793 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0513. Min Act: -0.0003

Data Index: 259246 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0519. Min Act: -0.0003

Data Index: 385775 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1006415 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0518. Min Act: -0.0003

Data Index: 565255 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0482. Min Act: -0.0003

Data Index: 487940 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1248560 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0612. Min Range: -0.0612

Max Act: 0.0473. Min Act: -0.0003

Data Index: 75258 (C4 (Web Text))

Max Activating Token Index: 379