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

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

Neuron 3856 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0001

Data Index: 768259 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0744. Min Act: -0.0001

Data Index: 796987 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0649. Min Act: -0.0001

Data Index: 417018 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0663. Min Act: -0.0001

Data Index: 285386 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1256968 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0654. Min Act: -0.0001

Data Index: 792698 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0579. Min Act: -0.0001

Data Index: 1299016 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0597. Min Act: -0.0001

Data Index: 706246 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0645. Min Act: -0.0001

Data Index: 742108 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0603. Min Act: -0.0001

Data Index: 880723 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0592. Min Act: -0.0001

Data Index: 643901 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0588. Min Act: -0.0001

Data Index: 329369 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0586. Min Act: -0.0001

Data Index: 249132 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0580. Min Act: -0.0001

Data Index: 105956 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0539. Min Act: -0.0001

Data Index: 508550 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1346066 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0528. Min Act: -0.0001

Data Index: 306113 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1161972 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0524. Min Act: -0.0001

Data Index: 729082 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0525. Min Act: -0.0001

Data Index: 211646 (C4 (Web Text))

Max Activating Token Index: 706