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

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

Neuron 3070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0002

Data Index: 18471 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0812. Min Act: -0.0002

Data Index: 844662 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0801. Min Act: -0.0002

Data Index: 986574 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0712. Min Act: -0.0002

Data Index: 696935 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0810. Min Act: -0.0002

Data Index: 126797 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0764. Min Act: -0.0002

Data Index: 551573 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0720. Min Act: -0.0002

Data Index: 384324 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0697. Min Act: -0.0002

Data Index: 910100 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0732. Min Act: -0.0002

Data Index: 938371 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0649. Min Act: -0.0002

Data Index: 248104 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0619. Min Act: -0.0002

Data Index: 104634 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1131951 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0712. Min Act: -0.0002

Data Index: 369709 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0761. Min Act: -0.0002

Data Index: 963767 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0686. Min Act: -0.0002

Data Index: 678352 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1147021 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0637. Min Act: -0.0002

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0561. Min Act: -0.0002

Data Index: 17471 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0630. Min Act: -0.0002

Data Index: 308920 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0574. Min Act: -0.0002

Data Index: 398850 (C4 (Web Text))

Max Activating Token Index: 752