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

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

Neuron 443 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1414. Min Act: -0.0001

Data Index: 361544 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1300947 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1437. Min Act: -0.0002

Data Index: 821205 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1361. Min Act: -0.0002

Data Index: 989797 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1363. Min Act: -0.0002

Data Index: 789252 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1418. Min Act: -0.0002

Data Index: 242998 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1584. Min Act: -0.0001

Data Index: 36454 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1305. Min Act: -0.0001

Data Index: 498809 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1265. Min Act: -0.0002

Data Index: 71399 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1121197 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1434. Min Act: -0.0002

Data Index: 1085746 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1429. Min Act: -0.0001

Data Index: 407165 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1421. Min Act: -0.0002

Data Index: 184159 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1359. Min Act: -0.0002

Data Index: 63473 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1262. Min Act: -0.0002

Data Index: 908001 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1204. Min Act: -0.0001

Data Index: 302047 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1340. Min Act: -0.0002

Data Index: 1033713 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1390. Min Act: -0.0001

Data Index: 528204 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1342. Min Act: -0.0002

Data Index: 338049 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.1584. Min Range: -0.1584

Max Act: 0.1386. Min Act: -0.0001

Data Index: 743873 (C4 (Web Text))

Max Activating Token Index: 16