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

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

Neuron 1760 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9976. Min Act: -0.0001

Data Index: 971161 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9871. Min Act: -0.0001

Data Index: 216691 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7001. Min Act: -0.0001

Data Index: 575922 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8002. Min Act: -0.0001

Data Index: 316085 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6996. Min Act: -0.0001

Data Index: 236788 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6989. Min Act: -0.0001

Data Index: 660243 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6645. Min Act: -0.0001

Data Index: 211299 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.5912. Min Act: -0.0001

Data Index: 957877 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6204. Min Act: -0.0001

Data Index: 145990 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6340. Min Act: -0.0001

Data Index: 467667 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.5679. Min Act: -0.0001

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6315. Min Act: -0.0001

Data Index: 1244071 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6313. Min Act: -0.0001

Data Index: 1162891 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6244. Min Act: -0.0001

Data Index: 751824 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1089403 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6135. Min Act: -0.0001

Data Index: 502595 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6309. Min Act: -0.0001

Data Index: 602369 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.6127. Min Act: -0.0001

Data Index: 386617 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.5651. Min Act: -0.0001

Data Index: 168774 (C4 (Web Text))

Max Activating Token Index: 132