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

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

Neuron 490 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1838. Min Act: -0.0001

Data Index: 518909 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1728. Min Act: -0.0001

Data Index: 710634 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1753. Min Act: -0.0001

Data Index: 373527 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1673. Min Act: -0.0001

Data Index: 514386 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1087327 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1484. Min Act: -0.0001

Data Index: 862753 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1475. Min Act: -0.0001

Data Index: 257598 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1131481 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1479. Min Act: -0.0001

Data Index: 878833 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1229142 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1365. Min Act: -0.0001

Data Index: 534858 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1038360 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1386. Min Act: -0.0001

Data Index: 935241 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1257649 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1371. Min Act: -0.0001

Data Index: 562927 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1355. Min Act: -0.0001

Data Index: 355849 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1409. Min Act: -0.0001

Data Index: 1063316 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1287. Min Act: -0.0001

Data Index: 985339 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1288. Min Act: -0.0001

Data Index: 613675 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1838. Min Range: -0.1838

Max Act: 0.1311. Min Act: -0.0001

Data Index: 600201 (C4 (Web Text))

Max Activating Token Index: 788