Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5483 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4353. Min Range: -2.4353

Max Act: 2.3467. Min Act: -0.0000

Data Index: 518028 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 2.4353. Min Range: -2.4353

Max Act: 2.4353. Min Act: 0.0000

Data Index: 1223770 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.4353. Min Range: -2.4353

Max Act: 2.2561. Min Act: -0.0000

Data Index: 1233608 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.9752. Min Act: -0.0000

Data Index: 1143162 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.9689. Min Act: -0.0000

Data Index: 1059574 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 2.4353. Min Range: -2.4353

Max Act: 2.1740. Min Act: -0.0000

Data Index: 840865 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 2.4353. Min Range: -2.4353

Max Act: 2.0589. Min Act: -0.0000

Data Index: 223925 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1019724 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.8061. Min Act: -0.0000

Data Index: 1355399 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.8751. Min Act: -0.0000

Data Index: 57787 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 2.4353. Min Range: -2.4353

Max Act: 2.0829. Min Act: -0.0000

Data Index: 1173356 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.7909. Min Act: -0.0000

Data Index: 1433227 (Python Code)

Max Activating Token Index: 539

Text #12

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.7591. Min Act: -0.0000

Data Index: 1059516 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.7423. Min Act: -0.0000

Data Index: 1493306 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.8132. Min Act: -0.0000

Data Index: 655096 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.6944. Min Act: -0.0000

Data Index: 400721 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.6791. Min Act: -0.0000

Data Index: 951150 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.5563. Min Act: -0.0000

Data Index: 342787 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.6488. Min Act: -0.0000

Data Index: 1091696 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 2.4353. Min Range: -2.4353

Max Act: 1.6408. Min Act: -0.0000

Data Index: 170651 (C4 (Web Text))

Max Activating Token Index: 233