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

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

Neuron 3696 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: 0.9373. Min Range: -0.9373

Max Act: 0.9296. Min Act: -0.0002

Data Index: 1621056 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9373. Min Act: -0.0002

Data Index: 1480934 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8870. Min Act: -0.0002

Data Index: 1564416 (Python Code)

Max Activating Token Index: 749

Text #3

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.9126. Min Act: -0.0002

Data Index: 1609104 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8990. Min Act: -0.0002

Data Index: 1602416 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8697. Min Act: -0.0002

Data Index: 1495033 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8733. Min Act: -0.0002

Data Index: 1647567 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8485. Min Act: -0.0002

Data Index: 1590737 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8669. Min Act: -0.0002

Data Index: 1504228 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8458. Min Act: -0.0002

Data Index: 1447988 (Python Code)

Max Activating Token Index: 214

Text #10

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8516. Min Act: -0.0002

Data Index: 1563125 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8329. Min Act: -0.0002

Data Index: 1596957 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8199. Min Act: -0.0002

Data Index: 1445385 (Python Code)

Max Activating Token Index: 326

Text #13

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8353. Min Act: -0.0002

Data Index: 1569013 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8224. Min Act: -0.0002

Data Index: 1607530 (Python Code)

Max Activating Token Index: 499

Text #15

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8280. Min Act: -0.0002

Data Index: 1378056 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8252. Min Act: -0.0002

Data Index: 1639445 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8230. Min Act: -0.0002

Data Index: 1552869 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8014. Min Act: -0.0002

Data Index: 1548901 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 0.9373. Min Range: -0.9373

Max Act: 0.8207. Min Act: -0.0002

Data Index: 1492259 (Python Code)

Max Activating Token Index: 934