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

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

Neuron 2106 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: 0.7247. Min Range: -0.7247

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1048543 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6470. Min Act: -0.0001

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6316. Min Act: -0.0001

Data Index: 1150606 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5428. Min Act: -0.0001

Data Index: 868090 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5246. Min Act: -0.0001

Data Index: 97618 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5717. Min Act: -0.0001

Data Index: 118184 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1075224 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5302. Min Act: -0.0001

Data Index: 489848 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5618. Min Act: -0.0001

Data Index: 1229345 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5144. Min Act: -0.0001

Data Index: 86922 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5213. Min Act: -0.0001

Data Index: 259571 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5197. Min Act: -0.0001

Data Index: 410464 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4808. Min Act: -0.0001

Data Index: 1126899 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5013. Min Act: -0.0001

Data Index: 391750 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4645. Min Act: -0.0001

Data Index: 426416 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4660. Min Act: -0.0001

Data Index: 525589 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4312. Min Act: -0.0001

Data Index: 549872 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4580. Min Act: -0.0001

Data Index: 1158720 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.4611. Min Act: -0.0001

Data Index: 128430 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.3837. Min Act: -0.0001

Data Index: 908503 (C4 (Web Text))

Max Activating Token Index: 720