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

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

Neuron 4279 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: 0.6111. Min Range: -0.6111

Max Act: 0.6079. Min Act: -0.0000

Data Index: 625621 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5899. Min Act: -0.0000

Data Index: 391117 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5116. Min Act: -0.0000

Data Index: 519448 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.6111. Min Act: -0.0000

Data Index: 841951 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5212. Min Act: -0.0000

Data Index: 930155 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5457. Min Act: -0.0000

Data Index: 309092 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5268. Min Act: -0.0000

Data Index: 615808 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1187544 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1274364 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4829. Min Act: -0.0000

Data Index: 509325 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1088705 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4948. Min Act: -0.0000

Data Index: 255690 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4713. Min Act: -0.0000

Data Index: 248727 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4498. Min Act: -0.0000

Data Index: 178801 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4762. Min Act: -0.0000

Data Index: 926969 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4714. Min Act: -0.0000

Data Index: 451333 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1349850 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4516. Min Act: -0.0000

Data Index: 571197 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4216. Min Act: -0.0000

Data Index: 502389 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.6111. Min Range: -0.6111

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1044708 (C4 (Web Text))

Max Activating Token Index: 394