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

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

Neuron 595 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: 1.3949. Min Range: -1.3949

Max Act: 1.3949. Min Act: -0.0000

Data Index: 1506032 (Python Code)

Max Activating Token Index: 655

Text #1

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.3671. Min Act: -0.0000

Data Index: 932361 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.3446. Min Act: -0.0000

Data Index: 378936 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1270339 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1215986 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.2002. Min Act: -0.0000

Data Index: 81968 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1950. Min Act: -0.0000

Data Index: 229656 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.2714. Min Act: -0.0000

Data Index: 642444 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1830. Min Act: -0.0000

Data Index: 150168 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.2265. Min Act: -0.0000

Data Index: 607775 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1964. Min Act: -0.0000

Data Index: 42350 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1981. Min Act: -0.0000

Data Index: 890990 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.0077. Min Act: -0.0000

Data Index: 579893 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1296483 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1799. Min Act: -0.0000

Data Index: 218701 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1586. Min Act: -0.0000

Data Index: 668002 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1286313 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.0797. Min Act: -0.0000

Data Index: 748088 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.2188. Min Act: -0.0000

Data Index: 170745 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.3949. Min Range: -1.3949

Max Act: 1.0782. Min Act: -0.0000

Data Index: 785683 (C4 (Web Text))

Max Activating Token Index: 826