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

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

Neuron 425 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0578. Min Act: -0.0006

Data Index: 465800 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0006

Data Index: 406303 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0573. Min Act: -0.0006

Data Index: 54500 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0575. Min Act: -0.0006

Data Index: 1087363 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0594. Min Act: -0.0006

Data Index: 516447 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0568. Min Act: -0.0006

Data Index: 1290740 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0538. Min Act: -0.0006

Data Index: 1310181 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0539. Min Act: -0.0006

Data Index: 495842 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0558. Min Act: -0.0006

Data Index: 1200799 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0559. Min Act: -0.0006

Data Index: 780678 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0528. Min Act: -0.0005

Data Index: 755939 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0553. Min Act: -0.0006

Data Index: 519349 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0548. Min Act: -0.0006

Data Index: 452739 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0551. Min Act: -0.0006

Data Index: 1277907 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0546. Min Act: -0.0006

Data Index: 1301601 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0542. Min Act: -0.0006

Data Index: 353824 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0564. Min Act: -0.0006

Data Index: 1113310 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0520. Min Act: -0.0006

Data Index: 719567 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0562. Min Act: -0.0005

Data Index: 1352483 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0515. Min Act: -0.0006

Data Index: 751276 (C4 (Web Text))

Max Activating Token Index: 829