Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1319525 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1303306 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2082. Min Act: -0.0000

Data Index: 649742 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1157590 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1992. Min Act: -0.0000

Data Index: 694885 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1831. Min Act: -0.0000

Data Index: 461093 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1841. Min Act: -0.0000

Data Index: 953705 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1309754 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1314097 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1691. Min Act: -0.0000

Data Index: 947863 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1553. Min Act: -0.0000

Data Index: 362409 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1604. Min Act: -0.0000

Data Index: 986219 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1559. Min Act: -0.0000

Data Index: 273498 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1616. Min Act: -0.0000

Data Index: 483683 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1556. Min Act: -0.0000

Data Index: 388545 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1499. Min Act: -0.0000

Data Index: 56966 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1149884 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1147916 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1265655 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1529. Min Act: -0.0000

Data Index: 361498 (C4 (Web Text))

Max Activating Token Index: 165