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

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

Neuron 3838 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0752. Min Act: -0.0002

Data Index: 996118 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0002

Data Index: 491719 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1040546 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0640. Min Act: -0.0002

Data Index: 349573 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1204348 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0571. Min Act: -0.0002

Data Index: 807570 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0562. Min Act: -0.0002

Data Index: 999509 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0554. Min Act: -0.0002

Data Index: 369882 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0593. Min Act: -0.0002

Data Index: 606858 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0570. Min Act: -0.0002

Data Index: 527406 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1041200 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0564. Min Act: -0.0002

Data Index: 466595 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0578. Min Act: -0.0002

Data Index: 725711 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1093846 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0536. Min Act: -0.0002

Data Index: 431251 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0536. Min Act: -0.0002

Data Index: 635177 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0553. Min Act: -0.0002

Data Index: 392063 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0544. Min Act: -0.0002

Data Index: 57142 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0529. Min Act: -0.0002

Data Index: 871902 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0517. Min Act: -0.0002

Data Index: 917576 (C4 (Web Text))

Max Activating Token Index: 278