Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 754 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1328. Min Act: -0.0004

Data Index: 27243 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1285. Min Act: -0.0004

Data Index: 828075 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1209. Min Act: -0.0004

Data Index: 854666 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1157. Min Act: -0.0004

Data Index: 15919 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1169. Min Act: -0.0004

Data Index: 1233956 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1137. Min Act: -0.0004

Data Index: 795733 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1110. Min Act: -0.0004

Data Index: 353524 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1096. Min Act: -0.0004

Data Index: 899058 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1069. Min Act: -0.0004

Data Index: 55226 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1099. Min Act: -0.0004

Data Index: 179085 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1105. Min Act: -0.0004

Data Index: 155160 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1093. Min Act: -0.0004

Data Index: 848757 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1052. Min Act: -0.0004

Data Index: 1293343 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1083. Min Act: -0.0004

Data Index: 1232729 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1037. Min Act: -0.0004

Data Index: 1007446 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1043. Min Act: -0.0004

Data Index: 171902 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1002. Min Act: -0.0004

Data Index: 1136626 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1078. Min Act: -0.0004

Data Index: 1115171 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1031. Min Act: -0.0004

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1018. Min Act: -0.0004

Data Index: 409270 (C4 (Web Text))

Max Activating Token Index: 947