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

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

Neuron 4360 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.3134. Min Act: -0.0000

Data Index: 506228 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2228. Min Act: -0.0000

Data Index: 366894 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2291. Min Act: -0.0000

Data Index: 78006 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2021. Min Act: -0.0000

Data Index: 725575 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2058. Min Act: -0.0000

Data Index: 139039 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1093364 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1938. Min Act: -0.0000

Data Index: 815725 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2066. Min Act: -0.0000

Data Index: 17786 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1977. Min Act: -0.0000

Data Index: 584310 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1918. Min Act: -0.0000

Data Index: 270945 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1097461 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1873. Min Act: -0.0000

Data Index: 699768 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1936. Min Act: -0.0000

Data Index: 1220567 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1803. Min Act: -0.0000

Data Index: 306085 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1279065 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1843. Min Act: -0.0000

Data Index: 731298 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1841. Min Act: -0.0000

Data Index: 397967 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1719. Min Act: -0.0000

Data Index: 735743 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1832. Min Act: -0.0000

Data Index: 134082 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1111639 (C4 (Web Text))

Max Activating Token Index: 980