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

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

Neuron 1660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2114. Min Act: -0.0000

Data Index: 216156 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2196. Min Act: -0.0000

Data Index: 640416 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2201. Min Act: -0.0000

Data Index: 70202 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1231146 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2160. Min Act: -0.0000

Data Index: 273485 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2137. Min Act: -0.0000

Data Index: 851212 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2089. Min Act: -0.0000

Data Index: 936223 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2163. Min Act: -0.0000

Data Index: 757430 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2082. Min Act: -0.0000

Data Index: 158314 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2128. Min Act: -0.0000

Data Index: 774940 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.2108. Min Act: -0.0000

Data Index: 239742 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1946. Min Act: -0.0000

Data Index: 715553 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1946. Min Act: -0.0000

Data Index: 648188 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1339157 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1080620 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1936. Min Act: -0.0000

Data Index: 185201 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1093322 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1300364 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1977. Min Act: -0.0000

Data Index: 814628 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.2201. Min Range: -0.2201

Max Act: 0.1863. Min Act: -0.0000

Data Index: 856196 (C4 (Web Text))

Max Activating Token Index: 720