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

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

Neuron 4523 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1533102 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1644130 (Python Code)

Max Activating Token Index: 565

Text #2

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1378800 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1526775 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1578378 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1462264 (Python Code)

Max Activating Token Index: 955

Text #6

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1546733 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1445557 (Python Code)

Max Activating Token Index: 633

Text #8

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1555279 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1467030 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1482723 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1550113 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3676. Min Act: -0.0000

Data Index: 1494005 (Python Code)

Max Activating Token Index: 369

Text #13

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1445502 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1466196 (Python Code)

Max Activating Token Index: 675

Text #15

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3295. Min Act: -0.0001

Data Index: 1603168 (Python Code)

Max Activating Token Index: 716

Text #16

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1535689 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1644815 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1426908 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1518276 (Python Code)

Max Activating Token Index: 945