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

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

Neuron 4310 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.2662. Min Act: -0.0000

Data Index: 474495 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1282662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.2329. Min Act: -0.0000

Data Index: 509630 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.2180. Min Act: -0.0000

Data Index: 936492 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.2720. Min Act: -0.0000

Data Index: 667608 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1926. Min Act: -0.0000

Data Index: 111618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1274637 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1029216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1684. Min Act: -0.0001

Data Index: 421826 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1172082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1286. Min Act: -0.0000

Data Index: 633384 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1444. Min Act: -0.0000

Data Index: 170209 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1238433 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1902. Min Act: -0.0000

Data Index: 381509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1197936 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1239585 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1154. Min Act: -0.0000

Data Index: 872416 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1274. Min Act: -0.0000

Data Index: 298299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1043017 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.4289. Min Range: -0.4289

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1008286 (C4 (Web Text))

Max Activating Token Index: 1023