Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1456837 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1650. Min Act: -0.0000

Data Index: 871191 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1702. Min Act: -0.0000

Data Index: 309743 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1561. Min Act: -0.0000

Data Index: 70047 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1345640 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1493178 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1455. Min Act: -0.0000

Data Index: 703993 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1954890 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1437. Min Act: -0.0000

Data Index: 993380 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1190857 (The Pile)

Max Activating Token Index: 371

Text #10

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1422. Min Act: -0.0001

Data Index: 870838 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1616562 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1398. Min Act: -0.0000

Data Index: 526432 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1501374 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1165196 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1311965 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1300507 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1533701 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1446. Min Act: -0.0000

Data Index: 488516 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.1761. Min Range: -0.1761

Max Act: 0.1405. Min Act: -0.0000

Data Index: 419555 (The Pile)

Max Activating Token Index: 533