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

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

Neuron 4026 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1229227 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1244148 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1251. Min Act: -0.0000

Data Index: 839910 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1272. Min Act: -0.0000

Data Index: 587066 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1232. Min Act: -0.0000

Data Index: 440827 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1047713 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1148. Min Act: -0.0000

Data Index: 729462 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1129. Min Act: -0.0001

Data Index: 162395 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1086. Min Act: -0.0001

Data Index: 657235 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1256476 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1137933 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1146. Min Act: -0.0000

Data Index: 45961 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1112. Min Act: -0.0000

Data Index: 796305 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1205262 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1030. Min Act: -0.0001

Data Index: 507400 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1028. Min Act: -0.0000

Data Index: 309204 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1106. Min Act: -0.0000

Data Index: 994163 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1136. Min Act: -0.0000

Data Index: 488535 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1101. Min Act: -0.0000

Data Index: 809375 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.2212. Min Range: -0.2212

Max Act: 0.1082. Min Act: -0.0001

Data Index: 246371 (C4 (Web Text))

Max Activating Token Index: 841