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

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

Neuron 2646 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.8888. Min Act: -0.0000

Data Index: 220978 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.8243. Min Act: -0.0000

Data Index: 1250287 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.6825. Min Act: -0.0000

Data Index: 924904 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.7426. Min Act: -0.0000

Data Index: 802193 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.8022. Min Act: -0.0000

Data Index: 464619 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.7117. Min Act: -0.0000

Data Index: 787621 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.8340. Min Act: -0.0000

Data Index: 418484 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.4247. Min Act: -0.0000

Data Index: 617717 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.6717. Min Act: -0.0000

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.4417. Min Act: -0.0000

Data Index: 240005 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.7460. Min Act: -0.0000

Data Index: 72896 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.4901. Min Act: -0.0000

Data Index: 1178395 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.2618. Min Act: -0.0000

Data Index: 544008 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.3840. Min Act: -0.0000

Data Index: 521046 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 4.8888. Min Range: -4.8888

Max Act: 3.9581. Min Act: -0.0000

Data Index: 962484 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.4492. Min Act: -0.0000

Data Index: 159728 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 4.8888. Min Range: -4.8888

Max Act: 3.9836. Min Act: -0.0000

Data Index: 479218 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.4846. Min Act: -0.0000

Data Index: 1246625 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.2771. Min Act: -0.0000

Data Index: 1159985 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 4.8888. Min Range: -4.8888

Max Act: 4.2544. Min Act: -0.0000

Data Index: 1317859 (C4 (Web Text))

Max Activating Token Index: 479