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

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

Neuron 125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1572349 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0741. Min Act: -0.0000

Data Index: 588347 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0560. Min Act: -0.0000

Data Index: 585820 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0698. Min Act: -0.0000

Data Index: 486876 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0654. Min Act: -0.0000

Data Index: 750561 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0655. Min Act: -0.0000

Data Index: 304750 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1306208 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0627. Min Act: -0.0000

Data Index: 78834 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0642. Min Act: -0.0000

Data Index: 742674 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0575. Min Act: -0.0000

Data Index: 280247 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1290208 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0559. Min Act: -0.0000

Data Index: 874079 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0553. Min Act: -0.0000

Data Index: 659034 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0553. Min Act: -0.0000

Data Index: 582153 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0549. Min Act: -0.0000

Data Index: 803382 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0517. Min Act: -0.0000

Data Index: 395009 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0494. Min Act: -0.0000

Data Index: 677412 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1614150 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1033501 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.0932. Min Range: -0.0932

Max Act: 0.0540. Min Act: -0.0000

Data Index: 642229 (C4 (Web Text))

Max Activating Token Index: 124