Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1146961 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2530. Min Act: -0.0000

Data Index: 473226 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1179733 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2235. Min Act: -0.0000

Data Index: 878366 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2231. Min Act: -0.0000

Data Index: 356981 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2235. Min Act: -0.0000

Data Index: 14844 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2095. Min Act: -0.0000

Data Index: 226752 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1279750 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1224577 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2250. Min Act: -0.0000

Data Index: 514691 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1275580 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2010. Min Act: -0.0000

Data Index: 737927 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1959. Min Act: -0.0000

Data Index: 42531 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1290579 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1358021 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1892. Min Act: -0.0000

Data Index: 304822 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1887. Min Act: -0.0000

Data Index: 923931 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1957. Min Act: -0.0000

Data Index: 928709 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1843. Min Act: -0.0000

Data Index: 674371 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.3179. Min Range: -0.3179

Max Act: 0.1961. Min Act: -0.0000

Data Index: 247847 (C4 (Web Text))

Max Activating Token Index: 820