Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1311 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0003

Data Index: 1565341 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1485963 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1177230 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0759. Min Act: -0.0003

Data Index: 1544630 (Python Code)

Max Activating Token Index: 701

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1121543 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0670. Min Act: -0.0003

Data Index: 622370 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1552549 (Python Code)

Max Activating Token Index: 389

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0672. Min Act: -0.0003

Data Index: 980141 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0662. Min Act: -0.0003

Data Index: 512210 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1588081 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0684. Min Act: -0.0004

Data Index: 994500 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0687. Min Act: -0.0004

Data Index: 1554151 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0626. Min Act: -0.0003

Data Index: 730074 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1514051 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1440086 (Python Code)

Max Activating Token Index: 137

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0652. Min Act: -0.0004

Data Index: 655588 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1561097 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1642194 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0628. Min Act: -0.0003

Data Index: 283680 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0653. Min Act: -0.0004

Data Index: 1127079 (C4 (Web Text))

Max Activating Token Index: 927