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

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

Neuron 4924 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1340. Min Act: -0.0002

Data Index: 1309370 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1105. Min Act: -0.0003

Data Index: 1355432 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0900. Min Act: -0.0003

Data Index: 697161 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0907. Min Act: -0.0003

Data Index: 481452 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0879. Min Act: -0.0003

Data Index: 384485 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0849. Min Act: -0.0002

Data Index: 556918 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0851. Min Act: -0.0003

Data Index: 1127172 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0846. Min Act: -0.0003

Data Index: 758902 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0831. Min Act: -0.0003

Data Index: 690326 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0803. Min Act: -0.0003

Data Index: 181793 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0814. Min Act: -0.0003

Data Index: 810395 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0813. Min Act: -0.0003

Data Index: 81980 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0768. Min Act: -0.0003

Data Index: 146682 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0839. Min Act: -0.0002

Data Index: 936679 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0775. Min Act: -0.0003

Data Index: 198003 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0773. Min Act: -0.0003

Data Index: 1354878 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0811. Min Act: -0.0003

Data Index: 386345 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1204971 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0756. Min Act: -0.0003

Data Index: 936540 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0774. Min Act: -0.0002

Data Index: 375496 (C4 (Web Text))

Max Activating Token Index: 434