Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1065 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0636. Min Act: -0.0005

Data Index: 201414 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0646. Min Act: -0.0005

Data Index: 989402 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0600. Min Act: -0.0005

Data Index: 616970 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0630. Min Act: -0.0005

Data Index: 641863 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0005

Data Index: 979422 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0599. Min Act: -0.0005

Data Index: 1331381 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0551. Min Act: -0.0005

Data Index: 84483 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0598. Min Act: -0.0005

Data Index: 63376 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0560. Min Act: -0.0005

Data Index: 186582 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0563. Min Act: -0.0005

Data Index: 1354611 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0539. Min Act: -0.0005

Data Index: 75119 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0550. Min Act: -0.0005

Data Index: 20305 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0537. Min Act: -0.0005

Data Index: 706759 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0528. Min Act: -0.0005

Data Index: 711080 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0559. Min Act: -0.0005

Data Index: 1094161 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0600. Min Act: -0.0005

Data Index: 382710 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0542. Min Act: -0.0005

Data Index: 127288 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0631. Min Act: -0.0005

Data Index: 95781 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0533. Min Act: -0.0005

Data Index: 1050471 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0577. Min Act: -0.0005

Data Index: 436096 (C4 (Web Text))

Max Activating Token Index: 740