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

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

Neuron 2241 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: 0.2345. Min Range: -0.2345

Max Act: 0.2345. Min Act: -0.0000

Data Index: 85143 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2127. Min Act: -0.0000

Data Index: 456835 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2075. Min Act: -0.0000

Data Index: 385323 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2189. Min Act: -0.0000

Data Index: 767644 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2023. Min Act: -0.0000

Data Index: 178154 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2043. Min Act: -0.0000

Data Index: 443785 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1957. Min Act: -0.0000

Data Index: 925740 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1874. Min Act: -0.0000

Data Index: 807412 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1957. Min Act: -0.0000

Data Index: 225110 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1946. Min Act: -0.0000

Data Index: 681301 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1837. Min Act: -0.0000

Data Index: 816003 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1702. Min Act: -0.0000

Data Index: 427172 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1739. Min Act: -0.0000

Data Index: 521768 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1684. Min Act: -0.0000

Data Index: 718172 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1756. Min Act: -0.0000

Data Index: 904951 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1695. Min Act: -0.0000

Data Index: 468387 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1649. Min Act: -0.0000

Data Index: 885259 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1599. Min Act: -0.0000

Data Index: 155255 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1553. Min Act: -0.0000

Data Index: 101879 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1290783 (C4 (Web Text))

Max Activating Token Index: 645