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

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

Neuron 2542 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.5416. Min Act: -0.0000

Data Index: 944973 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1212039 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1063810 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.4251. Min Act: -0.0000

Data Index: 905672 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.4222. Min Act: -0.0000

Data Index: 642862 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.4243. Min Act: -0.0000

Data Index: 381456 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.4179. Min Act: -0.0000

Data Index: 580398 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3816. Min Act: -0.0000

Data Index: 346075 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3863. Min Act: -0.0000

Data Index: 983166 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3698. Min Act: -0.0000

Data Index: 810972 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3743. Min Act: -0.0000

Data Index: 925935 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3692. Min Act: -0.0000

Data Index: 791554 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3544. Min Act: -0.0000

Data Index: 622491 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3453. Min Act: -0.0000

Data Index: 794952 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3296. Min Act: -0.0000

Data Index: 850652 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1190524 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3537. Min Act: -0.0000

Data Index: 499403 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1085378 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3350. Min Act: -0.0000

Data Index: 288447 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.5416. Min Range: -0.5416

Max Act: 0.3443. Min Act: -0.0000

Data Index: 849163 (C4 (Web Text))

Max Activating Token Index: 703