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

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

Neuron 3223 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1503795 (Python Code)

Max Activating Token Index: 167

Text #1

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1590900 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2191. Min Act: -0.0000

Data Index: 540946 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1051165 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1272516 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1064832 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1470914 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1378621 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1879. Min Act: -0.0000

Data Index: 339218 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1764. Min Act: -0.0000

Data Index: 160927 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1791. Min Act: -0.0000

Data Index: 455093 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1828. Min Act: -0.0000

Data Index: 822154 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1774. Min Act: -0.0000

Data Index: 279319 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1832. Min Act: -0.0000

Data Index: 336520 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1747. Min Act: -0.0000

Data Index: 212046 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1929. Min Act: -0.0000

Data Index: 76588 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1776. Min Act: -0.0000

Data Index: 135269 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1760. Min Act: -0.0000

Data Index: 448333 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1110389 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.3011. Min Range: -0.3011

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1489836 (Python Code)

Max Activating Token Index: 535