Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 149 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0002

Data Index: 453912 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0747. Min Act: -0.0002

Data Index: 291202 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0733. Min Act: -0.0002

Data Index: 904603 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0691. Min Act: -0.0002

Data Index: 312784 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0691. Min Act: -0.0002

Data Index: 517088 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0700. Min Act: -0.0002

Data Index: 655385 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0684. Min Act: -0.0002

Data Index: 203483 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0639. Min Act: -0.0002

Data Index: 954652 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0607. Min Act: -0.0002

Data Index: 517646 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1101266 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0626. Min Act: -0.0002

Data Index: 781087 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0647. Min Act: -0.0002

Data Index: 382413 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0635. Min Act: -0.0002

Data Index: 660665 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1051552 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0605. Min Act: -0.0002

Data Index: 207447 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0629. Min Act: -0.0002

Data Index: 327495 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0627. Min Act: -0.0002

Data Index: 676773 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0604. Min Act: -0.0002

Data Index: 128350 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0622. Min Act: -0.0002

Data Index: 645292 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0669. Min Act: -0.0002

Data Index: 895913 (C4 (Web Text))

Max Activating Token Index: 94