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

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

Neuron 829 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1460. Min Act: -0.0004

Data Index: 350012 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1592. Min Act: -0.0004

Data Index: 791733 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1592. Min Act: -0.0004

Data Index: 306373 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1550. Min Act: -0.0004

Data Index: 1306518 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1644. Min Act: -0.0004

Data Index: 238958 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1645. Min Act: -0.0004

Data Index: 27086 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1549. Min Act: -0.0004

Data Index: 23956 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1489. Min Act: -0.0004

Data Index: 1152768 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1255. Min Act: -0.0004

Data Index: 842277 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1459. Min Act: -0.0004

Data Index: 271300 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1409. Min Act: -0.0004

Data Index: 1119466 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1513. Min Act: -0.0004

Data Index: 517308 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1443. Min Act: -0.0004

Data Index: 582689 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1502. Min Act: -0.0004

Data Index: 909315 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1349. Min Act: -0.0004

Data Index: 1118961 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1446. Min Act: -0.0004

Data Index: 1135832 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1432. Min Act: -0.0004

Data Index: 288571 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1396. Min Act: -0.0004

Data Index: 463967 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1360. Min Act: -0.0004

Data Index: 228533 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1645. Min Range: -0.1645

Max Act: 0.1427. Min Act: -0.0004

Data Index: 651280 (C4 (Web Text))

Max Activating Token Index: 542