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

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

Neuron 3295 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1675. Min Act: -0.0000

Data Index: 426636 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1705. Min Act: -0.0000

Data Index: 941251 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1683. Min Act: -0.0000

Data Index: 325296 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1700. Min Act: -0.0000

Data Index: 665252 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1123943 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1740. Min Act: -0.0000

Data Index: 754687 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1060656 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1506. Min Act: -0.0000

Data Index: 553661 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1651. Min Act: -0.0000

Data Index: 235029 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1520. Min Act: -0.0000

Data Index: 493280 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1578. Min Act: -0.0000

Data Index: 33104 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1551. Min Act: -0.0000

Data Index: 929530 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1494. Min Act: -0.0000

Data Index: 749921 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1522. Min Act: -0.0000

Data Index: 733981 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1326. Min Act: -0.0000

Data Index: 447409 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1504. Min Act: -0.0000

Data Index: 27491 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1488. Min Act: -0.0000

Data Index: 811337 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1500. Min Act: -0.0000

Data Index: 303272 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1443. Min Act: -0.0000

Data Index: 533844 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.1740. Min Range: -0.1740

Max Act: 0.1484. Min Act: -0.0000

Data Index: 197438 (C4 (Web Text))

Max Activating Token Index: 199