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

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

Neuron 4312 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0760. Min Act: -0.0002

Data Index: 85239 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0747. Min Act: -0.0003

Data Index: 917873 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0715. Min Act: -0.0003

Data Index: 568676 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0725. Min Act: -0.0003

Data Index: 790271 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0688. Min Act: -0.0003

Data Index: 100957 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0685. Min Act: -0.0003

Data Index: 435498 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1145276 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0648. Min Act: -0.0003

Data Index: 144293 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0661. Min Act: -0.0003

Data Index: 418984 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0644. Min Act: -0.0003

Data Index: 20918 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0643. Min Act: -0.0003

Data Index: 665441 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0649. Min Act: -0.0003

Data Index: 382509 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0661. Min Act: -0.0003

Data Index: 475271 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0631. Min Act: -0.0003

Data Index: 829466 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0639. Min Act: -0.0003

Data Index: 326040 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0637. Min Act: -0.0003

Data Index: 658311 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0604. Min Act: -0.0003

Data Index: 381000 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0641. Min Act: -0.0003

Data Index: 651728 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1335207 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.0760. Min Range: -0.0760

Max Act: 0.0598. Min Act: -0.0003

Data Index: 107474 (C4 (Web Text))

Max Activating Token Index: 197