Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1382 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0001

Data Index: 843024 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1115511 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1084003 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0559. Min Act: -0.0001

Data Index: 484104 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0475. Min Act: -0.0001

Data Index: 920352 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0445. Min Act: -0.0001

Data Index: 195098 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1103739 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1225734 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0393. Min Act: -0.0001

Data Index: 445913 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0411. Min Act: -0.0001

Data Index: 214525 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1010228 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0392. Min Act: -0.0001

Data Index: 413877 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0403. Min Act: -0.0001

Data Index: 889513 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0397. Min Act: -0.0001

Data Index: 718964 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0380. Min Act: -0.0001

Data Index: 855407 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0393. Min Act: -0.0001

Data Index: 447045 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0396. Min Act: -0.0001

Data Index: 648747 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1158255 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1111507 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0366. Min Act: -0.0001

Data Index: 54038 (C4 (Web Text))

Max Activating Token Index: 726