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

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

Neuron 168 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0685. Min Act: -0.0002

Data Index: 222875 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0631. Min Act: -0.0002

Data Index: 974799 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0631. Min Act: -0.0002

Data Index: 977445 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1243774 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0626. Min Act: -0.0002

Data Index: 494062 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0610. Min Act: -0.0002

Data Index: 192781 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0595. Min Act: -0.0002

Data Index: 135887 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0604. Min Act: -0.0002

Data Index: 796548 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0591. Min Act: -0.0002

Data Index: 10362 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0578. Min Act: -0.0002

Data Index: 821418 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0584. Min Act: -0.0002

Data Index: 372054 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1351475 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1043080 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1274317 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0555. Min Act: -0.0002

Data Index: 899605 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0550. Min Act: -0.0002

Data Index: 103036 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1067520 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0534. Min Act: -0.0002

Data Index: 278345 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1313483 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0685. Min Range: -0.0685

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1348811 (C4 (Web Text))

Max Activating Token Index: 399