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

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

Neuron 2816 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3394. Min Act: -0.0000

Data Index: 1468198 (Python Code)

Max Activating Token Index: 609

Text #1

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3554. Min Act: -0.0000

Data Index: 1627823 (Python Code)

Max Activating Token Index: 430

Text #2

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3095. Min Act: -0.0000

Data Index: 1490552 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1517619 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3353. Min Act: -0.0000

Data Index: 1464071 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1480775 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1576209 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1506892 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2480. Min Act: -0.0000

Data Index: 1376663 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1522012 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1409713 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1377241 (Python Code)

Max Activating Token Index: 565

Text #12

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2521. Min Act: -0.0001

Data Index: 1648252 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1633387 (Python Code)

Max Activating Token Index: 381

Text #14

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1603625 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1405334 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1400009 (Python Code)

Max Activating Token Index: 392

Text #17

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1417980 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1477697 (Python Code)

Max Activating Token Index: 590

Text #19

Max Range: 1.3594. Min Range: -1.3594

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1601568 (Python Code)

Max Activating Token Index: 202