Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.8611. Min Act: -0.0000

Data Index: 750709 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.7638. Min Act: -0.0000

Data Index: 257556 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5041. Min Act: -0.0000

Data Index: 257169 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5378. Min Act: -0.0000

Data Index: 682532 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5783. Min Act: -0.0000

Data Index: 243227 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5498. Min Act: -0.0000

Data Index: 142602 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5200. Min Act: -0.0000

Data Index: 1131650 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.4302. Min Act: -0.0000

Data Index: 22821 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.5051. Min Act: -0.0000

Data Index: 60555 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1174581 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3380. Min Act: -0.0000

Data Index: 218068 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2345. Min Act: -0.0000

Data Index: 974973 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3911. Min Act: -0.0000

Data Index: 493712 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3197. Min Act: -0.0000

Data Index: 706757 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.4332. Min Act: -0.0000

Data Index: 276620 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3508. Min Act: -0.0000

Data Index: 866442 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3521. Min Act: -0.0000

Data Index: 647473 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1150457 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3293. Min Act: -0.0000

Data Index: 833541 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.8611. Min Range: -1.8611

Max Act: 1.3519. Min Act: -0.0000

Data Index: 702782 (C4 (Web Text))

Max Activating Token Index: 157