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

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

Neuron 121 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1785. Min Act: -0.0001

Data Index: 84543 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1634. Min Act: -0.0001

Data Index: 832647 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1555. Min Act: -0.0001

Data Index: 273382 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1202320 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1486. Min Act: -0.0001

Data Index: 839480 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1171790 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1462. Min Act: -0.0001

Data Index: 175615 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1021080 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1467. Min Act: -0.0001

Data Index: 195430 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1323012 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1079809 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1323. Min Act: -0.0001

Data Index: 229772 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1381. Min Act: -0.0001

Data Index: 472370 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1348. Min Act: -0.0001

Data Index: 21111 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1329. Min Act: -0.0001

Data Index: 517197 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1367. Min Act: -0.0001

Data Index: 994066 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1268. Min Act: -0.0001

Data Index: 456538 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1275. Min Act: -0.0001

Data Index: 310228 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1203695 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1075678 (C4 (Web Text))

Max Activating Token Index: 992