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

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

Neuron 3513 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1026874 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1248. Min Act: -0.0000

Data Index: 581841 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1208002 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1028. Min Act: -0.0000

Data Index: 251116 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1274041 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1487493 (Python Code)

Max Activating Token Index: 612

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0954. Min Act: -0.0000

Data Index: 973933 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1234142 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0740. Min Act: -0.0000

Data Index: 311327 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0686. Min Act: -0.0000

Data Index: 123352 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1440555 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1067162 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0666. Min Act: -0.0000

Data Index: 167861 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0704. Min Act: -0.0000

Data Index: 51897 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0643. Min Act: -0.0000

Data Index: 641552 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1526173 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0707. Min Act: -0.0000

Data Index: 790485 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0648. Min Act: -0.0000

Data Index: 434681 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1295562 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1359202 (C4 (Web Text))

Max Activating Token Index: 500