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

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

Neuron 3898 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.8373. Min Act: -0.0002

Data Index: 942484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.4622. Min Act: -0.0002

Data Index: 1405737 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.3629. Min Act: -0.0002

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.3984. Min Act: -0.0002

Data Index: 148998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.3234. Min Act: -0.0002

Data Index: 358068 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.3286. Min Act: -0.0002

Data Index: 134956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.3190. Min Act: -0.0002

Data Index: 1540841 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.3170. Min Act: -0.0002

Data Index: 322522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.2874. Min Act: -0.0002

Data Index: 59258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.2307. Min Act: -0.0002

Data Index: 30534 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.2475. Min Act: -0.0002

Data Index: 1649072 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1984. Min Act: -0.0002

Data Index: 588940 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1920. Min Act: -0.0002

Data Index: 62404 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1093572 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1519. Min Act: -0.0002

Data Index: 294545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1255. Min Act: -0.0002

Data Index: 668586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1278. Min Act: -0.0002

Data Index: 335531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1200. Min Act: -0.0002

Data Index: 747114 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.8373. Min Range: -0.8373

Max Act: 0.1158. Min Act: -0.0002

Data Index: 349581 (C4 (Web Text))

Max Activating Token Index: 1023