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

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

Neuron 2007 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: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0002

Data Index: 593307 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0718. Min Act: -0.0000

Data Index: 93609 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0696. Min Act: -0.0001

Data Index: 452746 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0680. Min Act: -0.0002

Data Index: 520554 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0669. Min Act: -0.0002

Data Index: 149095 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0670. Min Act: -0.0002

Data Index: 580098 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1292398 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1024362 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0652. Min Act: -0.0002

Data Index: 144463 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1049621 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0636. Min Act: -0.0001

Data Index: 343931 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1027771 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0608. Min Act: -0.0001

Data Index: 356414 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1335729 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0578. Min Act: -0.0002

Data Index: 830325 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0596. Min Act: -0.0002

Data Index: 296522 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0597. Min Act: -0.0002

Data Index: 769049 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0597. Min Act: -0.0002

Data Index: 873472 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0584. Min Act: -0.0002

Data Index: 866843 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0605. Min Act: -0.0002

Data Index: 715108 (C4 (Web Text))

Max Activating Token Index: 914