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

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

Neuron 3581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0001

Data Index: 516200 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1687. Min Act: -0.0001

Data Index: 357818 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1608. Min Act: -0.0000

Data Index: 944582 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1147640 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1579. Min Act: -0.0000

Data Index: 314698 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1570. Min Act: -0.0001

Data Index: 700812 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1687. Min Act: -0.0000

Data Index: 282960 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1678. Min Act: -0.0000

Data Index: 220255 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1458. Min Act: -0.0000

Data Index: 169380 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1542. Min Act: -0.0001

Data Index: 786932 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1432. Min Act: -0.0000

Data Index: 522468 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1432. Min Act: -0.0000

Data Index: 40919 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1361. Min Act: -0.0000

Data Index: 419220 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1440. Min Act: -0.0001

Data Index: 594953 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1162122 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1486. Min Act: -0.0001

Data Index: 74128 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1477. Min Act: -0.0001

Data Index: 312664 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1528. Min Act: -0.0001

Data Index: 832566 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1156. Min Act: -0.0001

Data Index: 388798 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1301. Min Act: -0.0000

Data Index: 463664 (C4 (Web Text))

Max Activating Token Index: 433