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

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

Neuron 2456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1327761 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0894. Min Act: -0.0000

Data Index: 917706 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0800. Min Act: -0.0000

Data Index: 28976 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0751. Min Act: -0.0000

Data Index: 945710 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0757. Min Act: -0.0000

Data Index: 34623 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0750. Min Act: -0.0000

Data Index: 64486 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0770. Min Act: -0.0000

Data Index: 482099 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0744. Min Act: -0.0000

Data Index: 250512 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0689. Min Act: -0.0000

Data Index: 698394 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1041411 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0671. Min Act: -0.0000

Data Index: 755047 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0631. Min Act: -0.0000

Data Index: 788104 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0727. Min Act: -0.0000

Data Index: 439313 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0679. Min Act: -0.0000

Data Index: 883131 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0676. Min Act: -0.0000

Data Index: 571656 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0651. Min Act: -0.0000

Data Index: 296890 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0735. Min Act: -0.0000

Data Index: 640948 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0710. Min Act: -0.0000

Data Index: 271501 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0656. Min Act: -0.0000

Data Index: 504675 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0614. Min Act: -0.0000

Data Index: 157232 (C4 (Web Text))

Max Activating Token Index: 276