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

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

Neuron 4364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0513. Min Act: -0.0000

Data Index: 1504643 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1335029 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0489. Min Act: -0.0000

Data Index: 1446106 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1483909 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1399206 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0434. Min Act: -0.0000

Data Index: 288742 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1506208 (Python Code)

Max Activating Token Index: 599

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1038189 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0409. Min Act: -0.0000

Data Index: 863047 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0404. Min Act: -0.0000

Data Index: 577240 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0413. Min Act: -0.0000

Data Index: 4728 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1591660 (Python Code)

Max Activating Token Index: 724

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1355763 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1406115 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0382. Min Act: -0.0000

Data Index: 122653 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1214349 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1546100 (Python Code)

Max Activating Token Index: 514

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0367. Min Act: -0.0000

Data Index: 685771 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0356. Min Act: -0.0000

Data Index: 331714 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0350. Min Act: -0.0000

Data Index: 693818 (C4 (Web Text))

Max Activating Token Index: 832