Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1417 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0651. Min Act: -0.0003

Data Index: 836112 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0637. Min Act: -0.0003

Data Index: 872965 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1328093 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0572. Min Act: -0.0003

Data Index: 364761 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0598. Min Act: -0.0003

Data Index: 346535 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0590. Min Act: -0.0004

Data Index: 910201 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1134018 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0572. Min Act: -0.0004

Data Index: 1196890 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0550. Min Act: -0.0002

Data Index: 221835 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0553. Min Act: -0.0004

Data Index: 1081463 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0541. Min Act: -0.0004

Data Index: 987262 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1167338 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0534. Min Act: -0.0003

Data Index: 517090 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1188795 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0523. Min Act: -0.0003

Data Index: 602569 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0504. Min Act: -0.0003

Data Index: 176495 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0522. Min Act: -0.0003

Data Index: 262871 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1350220 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0516. Min Act: -0.0004

Data Index: 974476 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1012535 (C4 (Web Text))

Max Activating Token Index: 447