Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1123 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0621. Min Act: -0.0003

Data Index: 727384 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0003

Data Index: 478730 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0589. Min Act: -0.0003

Data Index: 719583 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0610. Min Act: -0.0003

Data Index: 524382 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0554. Min Act: -0.0003

Data Index: 427657 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0548. Min Act: -0.0003

Data Index: 890820 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1282717 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0585. Min Act: -0.0003

Data Index: 213640 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0609. Min Act: -0.0003

Data Index: 365761 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0510. Min Act: -0.0003

Data Index: 187689 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1332308 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0530. Min Act: -0.0003

Data Index: 777338 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0545. Min Act: -0.0003

Data Index: 303776 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0519. Min Act: -0.0003

Data Index: 354271 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1103833 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0582. Min Act: -0.0003

Data Index: 877105 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0538. Min Act: -0.0003

Data Index: 814381 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0495. Min Act: -0.0003

Data Index: 116316 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0583. Min Act: -0.0003

Data Index: 736217 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1326071 (C4 (Web Text))

Max Activating Token Index: 840