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

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

Neuron 129 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: 0.5170. Min Range: -0.5170

Max Act: 0.5170. Min Act: -0.0000

Data Index: 795744 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.3359. Min Act: -0.0000

Data Index: 851398 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2602. Min Act: -0.0000

Data Index: 482235 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2482. Min Act: -0.0000

Data Index: 995198 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2538. Min Act: -0.0000

Data Index: 459184 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2506. Min Act: -0.0000

Data Index: 547854 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2594. Min Act: -0.0000

Data Index: 169016 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2126. Min Act: -0.0000

Data Index: 263229 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2198. Min Act: -0.0000

Data Index: 133383 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1168515 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2182. Min Act: -0.0000

Data Index: 604240 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2134. Min Act: -0.0000

Data Index: 342931 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1122187 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2135. Min Act: -0.0000

Data Index: 771757 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2115. Min Act: -0.0000

Data Index: 658594 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1346379 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1327170 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.1942. Min Act: -0.0000

Data Index: 86511 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1232947 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.5170. Min Range: -0.5170

Max Act: 0.2006. Min Act: -0.0000

Data Index: 307157 (C4 (Web Text))

Max Activating Token Index: 656