Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 106 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9079. Min Act: -0.0001

Data Index: 1060555 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9902. Min Act: -0.0001

Data Index: 712284 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9901. Min Act: -0.0001

Data Index: 934748 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9245. Min Act: -0.0001

Data Index: 837600 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9254. Min Act: -0.0001

Data Index: 1312132 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9484. Min Act: -0.0001

Data Index: 1123942 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8988. Min Act: -0.0001

Data Index: 1182155 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1176270 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8932. Min Act: -0.0001

Data Index: 164660 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8598. Min Act: -0.0001

Data Index: 41423 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8603. Min Act: -0.0001

Data Index: 1178944 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.9092. Min Act: -0.0001

Data Index: 742805 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8952. Min Act: -0.0001

Data Index: 854332 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8504. Min Act: -0.0001

Data Index: 70611 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8920. Min Act: -0.0001

Data Index: 729786 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8109. Min Act: -0.0001

Data Index: 987873 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8029. Min Act: -0.0001

Data Index: 797134 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8212. Min Act: -0.0001

Data Index: 364745 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.8065. Min Act: -0.0001

Data Index: 691968 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.9902. Min Range: -0.9902

Max Act: 0.7487. Min Act: -0.0001

Data Index: 843675 (C4 (Web Text))

Max Activating Token Index: 732