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

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

Neuron 3657 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: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0003

Data Index: 566427 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0662. Min Act: -0.0002

Data Index: 480788 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1155294 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1114177 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0660. Min Act: -0.0003

Data Index: 128850 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1352807 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1190800 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1044042 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1329971 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1223103 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0649. Min Act: -0.0003

Data Index: 342211 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0647. Min Act: -0.0003

Data Index: 327257 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0665. Min Act: -0.0003

Data Index: 828277 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0646. Min Act: -0.0003

Data Index: 214282 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0646. Min Act: -0.0003

Data Index: 59900 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1067479 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0639. Min Act: -0.0002

Data Index: 130020 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0613. Min Act: -0.0003

Data Index: 158186 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0602. Min Act: -0.0003

Data Index: 800166 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0636. Min Act: -0.0003

Data Index: 345525 (C4 (Web Text))

Max Activating Token Index: 968