Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1341 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1649. Min Act: -0.0001

Data Index: 479026 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1446. Min Act: -0.0001

Data Index: 139697 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1573. Min Act: -0.0001

Data Index: 833322 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1633. Min Act: -0.0001

Data Index: 170574 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1451. Min Act: -0.0001

Data Index: 193597 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1490. Min Act: -0.0001

Data Index: 317993 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1439. Min Act: -0.0001

Data Index: 149292 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1324. Min Act: -0.0001

Data Index: 788072 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1487. Min Act: -0.0001

Data Index: 221733 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1277. Min Act: -0.0001

Data Index: 832381 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1448. Min Act: -0.0001

Data Index: 82080 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1350. Min Act: -0.0001

Data Index: 391223 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1356. Min Act: -0.0001

Data Index: 545373 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1112414 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1339. Min Act: -0.0001

Data Index: 571099 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1352. Min Act: -0.0001

Data Index: 559016 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1389. Min Act: -0.0001

Data Index: 189311 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1392. Min Act: -0.0001

Data Index: 787316 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1341. Min Act: -0.0001

Data Index: 738383 (C4 (Web Text))

Max Activating Token Index: 131