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

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

Neuron 1684 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: 0.0679. Min Range: -0.0679

Max Act: 0.0677. Min Act: -0.0002

Data Index: 437684 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0663. Min Act: -0.0002

Data Index: 378767 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1038991 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0664. Min Act: -0.0002

Data Index: 488597 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: 0.0001

Data Index: 737269 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1314082 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1136800 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0652. Min Act: -0.0002

Data Index: 626966 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0634. Min Act: -0.0002

Data Index: 243314 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0646. Min Act: -0.0001

Data Index: 995656 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0622. Min Act: -0.0002

Data Index: 438875 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0614. Min Act: -0.0002

Data Index: 339493 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0613. Min Act: 0.0001

Data Index: 360709 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0624. Min Act: -0.0002

Data Index: 37010 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0621. Min Act: -0.0002

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0643. Min Act: -0.0002

Data Index: 131560 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0633. Min Act: -0.0002

Data Index: 778942 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0604. Min Act: -0.0002

Data Index: 39582 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0605. Min Act: -0.0002

Data Index: 531929 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0615. Min Act: -0.0001

Data Index: 288276 (C4 (Web Text))

Max Activating Token Index: 175