Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 979 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1307016 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0812. Min Act: -0.0000

Data Index: 577233 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0919. Min Act: -0.0001

Data Index: 791012 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1159401 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0755. Min Act: -0.0001

Data Index: 500675 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0735. Min Act: -0.0000

Data Index: 231327 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1150044 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1261708 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1096948 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1167 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0657. Min Act: -0.0000

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0669. Min Act: -0.0000

Data Index: 422512 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1192529 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1182849 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0620. Min Act: -0.0001

Data Index: 240637 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0638. Min Act: -0.0001

Data Index: 43719 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0656. Min Act: -0.0000

Data Index: 927743 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0600. Min Act: -0.0001

Data Index: 168268 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0742. Min Act: -0.0001

Data Index: 218463 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1054915 (C4 (Web Text))

Max Activating Token Index: 531