Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5218 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0000

Data Index: 518649 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1028714 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1196774 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1320293 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1606. Min Act: -0.0000

Data Index: 707256 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1634. Min Act: -0.0000

Data Index: 531397 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1614. Min Act: -0.0000

Data Index: 909581 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1322230 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1518. Min Act: -0.0000

Data Index: 115081 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1445. Min Act: -0.0000

Data Index: 103669 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1526. Min Act: -0.0000

Data Index: 823032 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1514. Min Act: -0.0000

Data Index: 696831 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1399. Min Act: -0.0000

Data Index: 201646 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1377. Min Act: -0.0000

Data Index: 277113 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1531. Min Act: -0.0000

Data Index: 134940 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1418. Min Act: -0.0000

Data Index: 541416 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1413. Min Act: -0.0000

Data Index: 959279 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1404. Min Act: -0.0000

Data Index: 479445 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1086225 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1077463 (C4 (Web Text))

Max Activating Token Index: 285