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

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

Neuron 499 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1477713 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1410998 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1121061 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.3284. Min Act: -0.0000

Data Index: 994864 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2298. Min Act: -0.0000

Data Index: 742134 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2335. Min Act: -0.0000

Data Index: 578356 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1603605 (Python Code)

Max Activating Token Index: 695

Text #7

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2053. Min Act: -0.0000

Data Index: 622403 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1504533 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1910. Min Act: -0.0000

Data Index: 140586 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1885. Min Act: -0.0000

Data Index: 804743 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1786. Min Act: -0.0000

Data Index: 758906 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1217437 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1177889 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1652. Min Act: -0.0000

Data Index: 999900 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1115598 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1650. Min Act: -0.0000

Data Index: 383770 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1633. Min Act: -0.0000

Data Index: 773417 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1561. Min Act: -0.0000

Data Index: 897171 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 0.4082. Min Range: -0.4082

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1113001 (C4 (Web Text))

Max Activating Token Index: 628