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

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

Neuron 485 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: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0005

Data Index: 921708 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0727. Min Act: -0.0005

Data Index: 126667 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0700. Min Act: -0.0005

Data Index: 269722 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0636. Min Act: -0.0005

Data Index: 900513 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0644. Min Act: -0.0005

Data Index: 21641 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0640. Min Act: -0.0005

Data Index: 403818 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0651. Min Act: -0.0005

Data Index: 744993 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0627. Min Act: -0.0005

Data Index: 467708 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0617. Min Act: -0.0005

Data Index: 894667 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0643. Min Act: -0.0005

Data Index: 531599 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0651. Min Act: -0.0005

Data Index: 743762 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0638. Min Act: -0.0005

Data Index: 544177 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0586. Min Act: -0.0005

Data Index: 523493 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0622. Min Act: -0.0005

Data Index: 504039 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0618. Min Act: -0.0005

Data Index: 1335827 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0655. Min Act: -0.0005

Data Index: 1244820 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0668. Min Act: -0.0005

Data Index: 222273 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0641. Min Act: -0.0005

Data Index: 1038486 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0623. Min Act: -0.0005

Data Index: 878124 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0621. Min Act: -0.0005

Data Index: 898220 (C4 (Web Text))

Max Activating Token Index: 943