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

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

Neuron 4070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9623. Min Act: -0.0001

Data Index: 689662 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9545. Min Act: -0.0001

Data Index: 686144 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8941. Min Act: -0.0001

Data Index: 1204581 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9190. Min Act: -0.0001

Data Index: 854078 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9154. Min Act: -0.0001

Data Index: 1071212 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1184851 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8803. Min Act: -0.0001

Data Index: 392986 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1067491 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8892. Min Act: -0.0001

Data Index: 624975 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8901. Min Act: -0.0001

Data Index: 132898 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.9177. Min Act: -0.0001

Data Index: 318372 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8720. Min Act: -0.0001

Data Index: 783595 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8411. Min Act: -0.0001

Data Index: 1095194 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8848. Min Act: -0.0001

Data Index: 766797 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8546. Min Act: -0.0001

Data Index: 1204389 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8327. Min Act: -0.0001

Data Index: 105109 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8457. Min Act: -0.0001

Data Index: 162865 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1242172 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1115541 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.9623. Min Range: -0.9623

Max Act: 0.8264. Min Act: -0.0001

Data Index: 1301888 (C4 (Web Text))

Max Activating Token Index: 809