Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4520 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1530. Min Act: -0.0001

Data Index: 118116 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1592. Min Act: -0.0001

Data Index: 859623 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0001

Data Index: 689483 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1501. Min Act: -0.0001

Data Index: 706084 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1544. Min Act: -0.0001

Data Index: 49294 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1469. Min Act: -0.0001

Data Index: 410973 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1486. Min Act: -0.0001

Data Index: 719277 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1597. Min Act: -0.0000

Data Index: 952845 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1590. Min Act: -0.0001

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1513. Min Act: -0.0001

Data Index: 717176 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1076567 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1503. Min Act: -0.0001

Data Index: 927524 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1714. Min Act: -0.0001

Data Index: 374827 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1482. Min Act: -0.0001

Data Index: 309962 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1339800 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1528. Min Act: -0.0001

Data Index: 19873 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1433. Min Act: -0.0001

Data Index: 458466 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1365. Min Act: -0.0001

Data Index: 698265 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1034656 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1646. Min Act: -0.0001

Data Index: 384871 (C4 (Web Text))

Max Activating Token Index: 632