Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 74 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0005

Data Index: 694181 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1522. Min Act: -0.0005

Data Index: 980394 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1506. Min Act: -0.0005

Data Index: 1277586 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1507. Min Act: -0.0005

Data Index: 15941 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1477. Min Act: -0.0005

Data Index: 497980 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1465. Min Act: -0.0005

Data Index: 949750 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1481. Min Act: -0.0005

Data Index: 986713 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1421. Min Act: -0.0005

Data Index: 421346 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1442. Min Act: -0.0005

Data Index: 1322803 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1365. Min Act: -0.0005

Data Index: 1242063 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1346. Min Act: -0.0005

Data Index: 83355 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1389. Min Act: -0.0005

Data Index: 527955 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1409. Min Act: -0.0005

Data Index: 476896 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1403. Min Act: -0.0005

Data Index: 793382 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1362. Min Act: -0.0005

Data Index: 186593 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1362. Min Act: -0.0005

Data Index: 477063 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1345. Min Act: -0.0005

Data Index: 102035 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1327. Min Act: -0.0005

Data Index: 551667 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1349. Min Act: -0.0005

Data Index: 984773 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1370. Min Act: -0.0005

Data Index: 138725 (C4 (Web Text))

Max Activating Token Index: 51