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

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

Neuron 3313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1728. Min Act: -0.0001

Data Index: 412637 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1093672 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1064641 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1610. Min Act: -0.0001

Data Index: 517412 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1579. Min Act: -0.0000

Data Index: 935732 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1499. Min Act: -0.0000

Data Index: 542295 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1471. Min Act: -0.0001

Data Index: 647522 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1477. Min Act: -0.0001

Data Index: 247951 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1501. Min Act: -0.0001

Data Index: 280908 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1394. Min Act: -0.0000

Data Index: 348755 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1430. Min Act: -0.0000

Data Index: 566492 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1226777 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1178922 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1158211 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1352703 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1328. Min Act: -0.0000

Data Index: 432468 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1417. Min Act: -0.0001

Data Index: 542827 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1306. Min Act: -0.0001

Data Index: 242578 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1349. Min Act: -0.0000

Data Index: 582850 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1339. Min Act: -0.0000

Data Index: 169587 (C4 (Web Text))

Max Activating Token Index: 13