Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1891 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8664. Min Act: -0.0000

Data Index: 709718 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.8085. Min Act: -0.0001

Data Index: 706778 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7494. Min Act: -0.0001

Data Index: 440923 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7349. Min Act: -0.0001

Data Index: 826677 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7539. Min Act: -0.0000

Data Index: 852452 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7219. Min Act: -0.0000

Data Index: 587013 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7052. Min Act: -0.0001

Data Index: 953003 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1137982 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6871. Min Act: -0.0000

Data Index: 937275 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1046556 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1258574 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6775. Min Act: -0.0001

Data Index: 303427 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6938. Min Act: -0.0000

Data Index: 434896 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1159804 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6847. Min Act: -0.0001

Data Index: 135064 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.7167. Min Act: -0.0000

Data Index: 371566 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6908. Min Act: -0.0001

Data Index: 212815 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6593. Min Act: -0.0001

Data Index: 338501 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6630. Min Act: -0.0001

Data Index: 687468 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.8664. Min Range: -0.8664

Max Act: 0.6697. Min Act: -0.0000

Data Index: 684667 (C4 (Web Text))

Max Activating Token Index: 688