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

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

Neuron 974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1188353 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0661. Min Act: -0.0001

Data Index: 341180 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1073720 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0658. Min Act: 0.0000

Data Index: 1158601 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0608. Min Act: -0.0001

Data Index: 843983 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0695. Min Act: -0.0001

Data Index: 89756 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0624. Min Act: -0.0001

Data Index: 657692 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0571. Min Act: -0.0001

Data Index: 394619 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0621. Min Act: -0.0001

Data Index: 967179 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1275535 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1271777 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0575. Min Act: 0.0001

Data Index: 527284 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0554. Min Act: -0.0000

Data Index: 696630 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0544. Min Act: -0.0001

Data Index: 239725 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1187704 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0559. Min Act: -0.0001

Data Index: 437138 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1168228 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0548. Min Act: -0.0001

Data Index: 868437 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0537. Min Act: -0.0001

Data Index: 289096 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1014. Min Range: -0.1014

Max Act: 0.0538. Min Act: -0.0001

Data Index: 34679 (C4 (Web Text))

Max Activating Token Index: 256