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

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

Neuron 3255 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0724. Min Act: -0.0000

Data Index: 658557 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0000

Data Index: 899743 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1084619 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1331870 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0635. Min Act: -0.0000

Data Index: 98608 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1002044 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1359422 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0606. Min Act: -0.0000

Data Index: 681636 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1159253 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1065107 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1010074 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0593. Min Act: -0.0000

Data Index: 232371 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0638. Min Act: -0.0000

Data Index: 218919 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0565. Min Act: -0.0000

Data Index: 90635 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1099365 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0586. Min Act: -0.0000

Data Index: 469070 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1228357 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0535. Min Act: -0.0000

Data Index: 580726 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0536. Min Act: -0.0000

Data Index: 276028 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0550. Min Act: -0.0000

Data Index: 813111 (C4 (Web Text))

Max Activating Token Index: 791