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

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

Neuron 2441 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0726. Min Act: -0.0001

Data Index: 33809 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0741. Min Act: -0.0000

Data Index: 747942 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0662. Min Act: -0.0001

Data Index: 266426 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1161261 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0658. Min Act: -0.0000

Data Index: 324725 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0653. Min Act: -0.0000

Data Index: 60092 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0653. Min Act: -0.0000

Data Index: 117660 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1230347 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1165805 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1177993 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0665. Min Act: -0.0000

Data Index: 528405 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0617. Min Act: -0.0000

Data Index: 103449 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: -0.0000

Data Index: 180149 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0626. Min Act: -0.0000

Data Index: 428006 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1183272 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0616. Min Act: -0.0000

Data Index: 930776 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0624. Min Act: -0.0001

Data Index: 992523 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1345115 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0599. Min Act: -0.0001

Data Index: 820544 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0555. Min Act: -0.0000

Data Index: 171880 (C4 (Web Text))

Max Activating Token Index: 613