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

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

Neuron 3036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1977. Min Act: -0.0001

Data Index: 574457 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1855. Min Act: -0.0001

Data Index: 745916 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1795. Min Act: -0.0001

Data Index: 653854 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1295312 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1766. Min Act: -0.0001

Data Index: 1214668 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1682. Min Act: -0.0001

Data Index: 653901 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1319245 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1776. Min Act: -0.0001

Data Index: 277766 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1587. Min Act: -0.0001

Data Index: 125215 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1720. Min Act: -0.0001

Data Index: 854912 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1271650 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1660. Min Act: -0.0001

Data Index: 799927 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1660. Min Act: -0.0001

Data Index: 957792 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1595. Min Act: -0.0001

Data Index: 423796 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1134400 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1581. Min Act: -0.0001

Data Index: 649110 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1260659 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1538. Min Act: -0.0001

Data Index: 999931 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1589. Min Act: -0.0001

Data Index: 101969 (C4 (Web Text))

Max Activating Token Index: 78