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

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

Neuron 1334 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: 1.8398. Min Range: -1.8398

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1626702 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1619155 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.5605. Min Act: -0.0000

Data Index: 1525880 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4990. Min Act: -0.0000

Data Index: 1364630 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1473656 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4008. Min Act: -0.0000

Data Index: 1411756 (Python Code)

Max Activating Token Index: 736

Text #6

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4463. Min Act: -0.0000

Data Index: 1590318 (Python Code)

Max Activating Token Index: 112

Text #7

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1614426 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4573. Min Act: -0.0000

Data Index: 1376887 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4371. Min Act: -0.0000

Data Index: 1587039 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1602983 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1596894 (Python Code)

Max Activating Token Index: 283

Text #12

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1483632 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1429947 (Python Code)

Max Activating Token Index: 764

Text #14

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3563. Min Act: -0.0000

Data Index: 1383210 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1644866 (Python Code)

Max Activating Token Index: 514

Text #16

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1574016 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1417960 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1637236 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 1.8398. Min Range: -1.8398

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1439419 (Python Code)

Max Activating Token Index: 396