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

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

Neuron 2004 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: 0.0711. Min Range: -0.0711

Max Act: 0.0708. Min Act: -0.0002

Data Index: 277162 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0692. Min Act: -0.0002

Data Index: 370636 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1254069 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0687. Min Act: -0.0001

Data Index: 212810 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0644. Min Act: -0.0002

Data Index: 875868 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0635. Min Act: -0.0002

Data Index: 7238 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0641. Min Act: -0.0002

Data Index: 143680 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0630. Min Act: -0.0002

Data Index: 537417 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0623. Min Act: -0.0002

Data Index: 128205 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0600. Min Act: -0.0001

Data Index: 890676 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0650. Min Act: -0.0002

Data Index: 890066 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0595. Min Act: -0.0002

Data Index: 687019 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0621. Min Act: -0.0002

Data Index: 153399 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1106412 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1019000 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1153861 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1132043 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0581. Min Act: -0.0002

Data Index: 378026 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0599. Min Act: -0.0002

Data Index: 805183 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1237472 (C4 (Web Text))

Max Activating Token Index: 519