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

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

Neuron 3342 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: 1.8598. Min Range: -1.8598

Max Act: 1.8073. Min Act: -0.0001

Data Index: 709322 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6002. Min Act: -0.0001

Data Index: 378217 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.8598. Min Act: -0.0001

Data Index: 932192 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7687. Min Act: -0.0001

Data Index: 37502 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7830. Min Act: -0.0001

Data Index: 854190 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6359. Min Act: -0.0001

Data Index: 896359 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7580. Min Act: -0.0001

Data Index: 1057646 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6595. Min Act: -0.0001

Data Index: 335302 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7133. Min Act: -0.0001

Data Index: 481810 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6779. Min Act: -0.0001

Data Index: 90373 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6873. Min Act: -0.0001

Data Index: 1161268 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6329. Min Act: -0.0001

Data Index: 1109648 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7068. Min Act: -0.0001

Data Index: 1114005 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6672. Min Act: -0.0001

Data Index: 213996 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.5927. Min Act: -0.0001

Data Index: 294887 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6497. Min Act: -0.0001

Data Index: 326497 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6987. Min Act: -0.0001

Data Index: 30961 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6883. Min Act: -0.0001

Data Index: 13386 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.6854. Min Act: -0.0001

Data Index: 288270 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.8598. Min Range: -1.8598

Max Act: 1.7252. Min Act: -0.0001

Data Index: 1320722 (C4 (Web Text))

Max Activating Token Index: 375