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

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

Neuron 3922 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: 0.9691. Min Range: -0.9691

Max Act: 0.9691. Min Act: -0.0001

Data Index: 762225 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8224. Min Act: -0.0001

Data Index: 1023670 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8108. Min Act: -0.0001

Data Index: 321166 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1093715 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8227. Min Act: -0.0001

Data Index: 305850 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7689. Min Act: -0.0001

Data Index: 1082881 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7384. Min Act: -0.0001

Data Index: 93976 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7204. Min Act: -0.0001

Data Index: 951779 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6752. Min Act: -0.0001

Data Index: 1266051 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7087. Min Act: -0.0001

Data Index: 595075 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7009. Min Act: -0.0001

Data Index: 1089020 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6737. Min Act: -0.0001

Data Index: 1335195 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1295246 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7164. Min Act: -0.0001

Data Index: 908657 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6343. Min Act: -0.0001

Data Index: 871011 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6887. Min Act: -0.0001

Data Index: 264856 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7063. Min Act: -0.0001

Data Index: 144765 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1172227 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6451. Min Act: -0.0001

Data Index: 1270709 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6748. Min Act: -0.0001

Data Index: 627255 (C4 (Web Text))

Max Activating Token Index: 977