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

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

Neuron 3376 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: 0.1912. Min Range: -0.1912

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1620372 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1673. Min Act: -0.0000

Data Index: 147336 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1204. Min Act: -0.0000

Data Index: 1317018 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1106637 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1176. Min Act: -0.0000

Data Index: 732377 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1272713 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1118737 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1039. Min Act: -0.0000

Data Index: 688379 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0897. Min Act: -0.0000

Data Index: 174476 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1340547 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0943. Min Act: -0.0000

Data Index: 675626 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0957. Min Act: -0.0000

Data Index: 781013 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1608923 (Python Code)

Max Activating Token Index: 942

Text #13

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0997. Min Act: -0.0000

Data Index: 826712 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1080836 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0959. Min Act: -0.0000

Data Index: 156469 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0896. Min Act: -0.0000

Data Index: 963111 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0908. Min Act: -0.0000

Data Index: 602633 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0967. Min Act: -0.0000

Data Index: 155309 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1497464 (Python Code)

Max Activating Token Index: 974