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

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

Neuron 470 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1009. Min Range: -7.1009

Max Act: 7.1009. Min Act: -0.0000

Data Index: 1277094 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.8959. Min Act: -0.0000

Data Index: 546083 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.1380. Min Act: -0.0000

Data Index: 896230 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.8909. Min Act: -0.0000

Data Index: 556270 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.6453. Min Act: -0.0000

Data Index: 426718 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.4493. Min Act: -0.0000

Data Index: 744493 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.0844. Min Act: -0.0000

Data Index: 370198 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 7.1009. Min Range: -7.1009

Max Act: 6.2696. Min Act: -0.0000

Data Index: 757041 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 7.1009. Min Range: -7.1009

Max Act: 5.9831. Min Act: -0.0000

Data Index: 77962 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 7.1009. Min Range: -7.1009

Max Act: 5.9649. Min Act: -0.0000

Data Index: 604416 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 7.1009. Min Range: -7.1009

Max Act: 5.4216. Min Act: -0.0000

Data Index: 218196 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 7.1009. Min Range: -7.1009

Max Act: 2.2578. Min Act: -0.0000

Data Index: 728345 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 7.1009. Min Range: -7.1009

Max Act: 2.4436. Min Act: -0.0000

Data Index: 350906 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 7.1009. Min Range: -7.1009

Max Act: 2.3684. Min Act: -0.0000

Data Index: 1277728 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 7.1009. Min Range: -7.1009

Max Act: 2.1078. Min Act: -0.0000

Data Index: 633416 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 7.1009. Min Range: -7.1009

Max Act: 1.3822. Min Act: -0.0000

Data Index: 279365 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 7.1009. Min Range: -7.1009

Max Act: 1.5156. Min Act: -0.0000

Data Index: 332580 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 7.1009. Min Range: -7.1009

Max Act: 1.3672. Min Act: -0.0000

Data Index: 787164 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 7.1009. Min Range: -7.1009

Max Act: 1.4404. Min Act: -0.0000

Data Index: 534773 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 7.1009. Min Range: -7.1009

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1028080 (C4 (Web Text))

Max Activating Token Index: 554