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

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

Neuron 5368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0730. Min Act: -0.0000

Data Index: 516279 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0696. Min Act: -0.0000

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0799. Min Act: -0.0000

Data Index: 610828 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0776. Min Act: -0.0000

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0000

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1098971 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1285778 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1255926 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1579361 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1530210 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1362759 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1602528 (Python Code)

Max Activating Token Index: 703

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1544264 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0543. Min Act: -0.0000

Data Index: 126553 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1538430 (Python Code)

Max Activating Token Index: 506

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1201740 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0578. Min Act: -0.0000

Data Index: 146940 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0666. Min Act: -0.0000

Data Index: 645113 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0677. Min Act: -0.0000

Data Index: 805142 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0662. Min Act: -0.0000

Data Index: 305608 (C4 (Web Text))

Max Activating Token Index: 447