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

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

Neuron 5897 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.1011. Min Act: -0.0002

Data Index: 1567701 (Python Code)

Max Activating Token Index: 489

Text #1

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.1019. Min Act: -0.0002

Data Index: 1562098 (Python Code)

Max Activating Token Index: 580

Text #2

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0650. Min Act: -0.0002

Data Index: 1627807 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0698. Min Act: -0.0002

Data Index: 1535916 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0627. Min Act: -0.0002

Data Index: 1644729 (Python Code)

Max Activating Token Index: 324

Text #5

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0369. Min Act: -0.0002

Data Index: 1433507 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0526. Min Act: -0.0002

Data Index: 1584138 (Python Code)

Max Activating Token Index: 506

Text #7

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0714. Min Act: -0.0002

Data Index: 1572492 (Python Code)

Max Activating Token Index: 329

Text #8

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0464. Min Act: -0.0002

Data Index: 1440777 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0447. Min Act: -0.0002

Data Index: 1576619 (Python Code)

Max Activating Token Index: 449

Text #10

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0375. Min Act: -0.0002

Data Index: 1655537 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0399. Min Act: -0.0002

Data Index: 1475793 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0546. Min Act: -0.0002

Data Index: 1586244 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0416. Min Act: -0.0002

Data Index: 1435842 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0236. Min Act: -0.0002

Data Index: 1450586 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0356. Min Act: -0.0002

Data Index: 1583500 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0373. Min Act: -0.0002

Data Index: 1602387 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0398. Min Act: -0.0002

Data Index: 1557411 (Python Code)

Max Activating Token Index: 369

Text #18

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0172. Min Act: -0.0002

Data Index: 1450930 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.0319. Min Act: -0.0002

Data Index: 1472787 (Python Code)

Max Activating Token Index: 456