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

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

Neuron 3587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0000

Data Index: 544623 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0000

Data Index: 557327 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1566. Min Act: -0.0000

Data Index: 895299 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1355323 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1584. Min Act: -0.0000

Data Index: 832827 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1002443 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1470. Min Act: -0.0000

Data Index: 873697 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1513. Min Act: -0.0001

Data Index: 639615 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1421. Min Act: -0.0000

Data Index: 486962 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1398. Min Act: -0.0000

Data Index: 486690 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1414. Min Act: -0.0000

Data Index: 635159 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1383. Min Act: -0.0000

Data Index: 238037 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1393. Min Act: -0.0000

Data Index: 165126 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1376. Min Act: -0.0001

Data Index: 909953 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1090954 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1377. Min Act: -0.0001

Data Index: 650352 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1285. Min Act: -0.0001

Data Index: 450755 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1292. Min Act: -0.0000

Data Index: 1101766 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1278. Min Act: -0.0000

Data Index: 1192010 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1170. Min Act: -0.0001

Data Index: 761890 (C4 (Web Text))

Max Activating Token Index: 251