Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5112 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0001

Data Index: 455077 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0822. Min Act: -0.0001

Data Index: 162561 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1038477 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0846. Min Act: -0.0001

Data Index: 890712 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0689. Min Act: -0.0001

Data Index: 684364 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0685. Min Act: -0.0001

Data Index: 273118 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0758. Min Act: -0.0001

Data Index: 237344 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0707. Min Act: -0.0001

Data Index: 186859 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0634. Min Act: -0.0001

Data Index: 819379 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0725. Min Act: -0.0002

Data Index: 918201 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0544. Min Act: -0.0001

Data Index: 64346 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0564. Min Act: -0.0001

Data Index: 70262 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0544. Min Act: -0.0001

Data Index: 791773 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0559. Min Act: -0.0001

Data Index: 992938 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0599. Min Act: -0.0001

Data Index: 779645 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1302013 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0601. Min Act: -0.0001

Data Index: 563407 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0677. Min Act: -0.0001

Data Index: 812905 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1142487 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0713. Min Act: -0.0001

Data Index: 855857 (C4 (Web Text))

Max Activating Token Index: 819