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

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

Neuron 5630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.1689. Min Act: -0.0000

Data Index: 779979 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.1280. Min Act: -0.0001

Data Index: 777546 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.1689. Min Range: -1.1689

Max Act: 1.0793. Min Act: -0.0000

Data Index: 351254 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1318970 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8999. Min Act: -0.0001

Data Index: 868690 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9230. Min Act: -0.0000

Data Index: 615902 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8003. Min Act: -0.0000

Data Index: 445912 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.9948. Min Act: -0.0000

Data Index: 981848 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8028. Min Act: -0.0000

Data Index: 582405 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8024. Min Act: -0.0000

Data Index: 723901 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1020836 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8409. Min Act: -0.0000

Data Index: 963089 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.7582. Min Act: -0.0000

Data Index: 435032 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8282. Min Act: -0.0000

Data Index: 914239 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8353. Min Act: -0.0001

Data Index: 785227 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8051. Min Act: -0.0000

Data Index: 773164 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.8282. Min Act: -0.0000

Data Index: 379705 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.7542. Min Act: -0.0000

Data Index: 378725 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1260018 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.1689. Min Range: -1.1689

Max Act: 0.7991. Min Act: -0.0000

Data Index: 302078 (C4 (Web Text))

Max Activating Token Index: 525