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

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

Neuron 4242 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: 0.1896. Min Range: -0.1896

Max Act: 0.1769. Min Act: -0.0000

Data Index: 104538 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1692. Min Act: -0.0000

Data Index: 428564 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1729. Min Act: -0.0000

Data Index: 149420 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1227412 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1556. Min Act: -0.0000

Data Index: 118003 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1600. Min Act: -0.0000

Data Index: 332275 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1443. Min Act: -0.0000

Data Index: 173744 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1567. Min Act: -0.0000

Data Index: 556341 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1177147 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1608. Min Act: -0.0000

Data Index: 960198 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1461. Min Act: -0.0000

Data Index: 348114 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1379. Min Act: -0.0000

Data Index: 695502 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1421. Min Act: -0.0000

Data Index: 398315 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1408. Min Act: -0.0000

Data Index: 689418 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1356. Min Act: -0.0000

Data Index: 206289 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1409. Min Act: -0.0000

Data Index: 903438 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1404. Min Act: -0.0000

Data Index: 791987 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1446. Min Act: -0.0000

Data Index: 164209 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1263. Min Act: -0.0000

Data Index: 819023 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1413. Min Act: -0.0000

Data Index: 861215 (C4 (Web Text))

Max Activating Token Index: 403