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

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

Neuron 1583 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0722. Min Act: -0.0001

Data Index: 456307 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1006579 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1248743 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0657. Min Act: -0.0001

Data Index: 650832 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0641. Min Act: -0.0001

Data Index: 438560 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1908 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0590. Min Act: -0.0001

Data Index: 81652 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1277846 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1057415 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0627. Min Act: -0.0001

Data Index: 514676 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0645. Min Act: -0.0001

Data Index: 750983 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1317067 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0618. Min Act: -0.0001

Data Index: 882471 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1274635 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0598. Min Act: -0.0001

Data Index: 820256 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1289054 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0556. Min Act: -0.0001

Data Index: 141767 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1354509 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0616. Min Act: -0.0001

Data Index: 788098 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0578. Min Act: -0.0001

Data Index: 496489 (C4 (Web Text))

Max Activating Token Index: 336