Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2239 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1951. Min Act: -0.0001

Data Index: 99443 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2082. Min Act: -0.0001

Data Index: 679736 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1744. Min Act: -0.0001

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1642. Min Act: -0.0001

Data Index: 971897 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1301388 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1708. Min Act: -0.0001

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1166091 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1569. Min Act: -0.0001

Data Index: 691764 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1552. Min Act: -0.0001

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1511. Min Act: -0.0001

Data Index: 955450 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1485. Min Act: -0.0001

Data Index: 348375 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1112877 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1458. Min Act: -0.0000

Data Index: 288224 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1176154 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1508. Min Act: -0.0000

Data Index: 329148 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1493. Min Act: -0.0001

Data Index: 415947 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1495. Min Act: -0.0001

Data Index: 233089 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1484. Min Act: -0.0001

Data Index: 736016 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1420. Min Act: -0.0001

Data Index: 912667 (C4 (Web Text))

Max Activating Token Index: 178