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

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

Neuron 676 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: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0002

Data Index: 327059 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0700. Min Act: -0.0002

Data Index: 661785 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0693. Min Act: -0.0002

Data Index: 50136 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0634. Min Act: -0.0002

Data Index: 95304 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0687. Min Act: -0.0002

Data Index: 43563 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0661. Min Act: -0.0002

Data Index: 105822 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0651. Min Act: -0.0002

Data Index: 38634 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0616. Min Act: -0.0002

Data Index: 997418 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0629. Min Act: -0.0002

Data Index: 369200 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0662. Min Act: -0.0002

Data Index: 339144 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0644. Min Act: -0.0001

Data Index: 627711 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0613. Min Act: -0.0002

Data Index: 6132 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0579. Min Act: -0.0002

Data Index: 813680 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0660. Min Act: -0.0002

Data Index: 531770 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1057209 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0624. Min Act: -0.0002

Data Index: 784542 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0608. Min Act: -0.0002

Data Index: 793023 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0609. Min Act: -0.0002

Data Index: 17767 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0608. Min Act: -0.0002

Data Index: 233643 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0626. Min Act: -0.0002

Data Index: 869835 (C4 (Web Text))

Max Activating Token Index: 773