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

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

Neuron 4555 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8113. Min Act: -0.0000

Data Index: 767015 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.8482. Min Act: -0.0000

Data Index: 829619 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.7996. Min Act: -0.0000

Data Index: 747835 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6490. Min Act: -0.0000

Data Index: 926314 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6005. Min Act: -0.0000

Data Index: 992564 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6140. Min Act: -0.0000

Data Index: 1257125 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6103. Min Act: -0.0000

Data Index: 50994 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6029. Min Act: -0.0000

Data Index: 521711 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6826. Min Act: -0.0000

Data Index: 90168 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5942. Min Act: -0.0000

Data Index: 825911 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5323. Min Act: -0.0000

Data Index: 1052904 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5460. Min Act: -0.0000

Data Index: 333957 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.4816. Min Act: -0.0000

Data Index: 416393 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6308. Min Act: -0.0000

Data Index: 370855 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1165936 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5405. Min Act: -0.0000

Data Index: 578242 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5378. Min Act: -0.0000

Data Index: 347305 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.5769. Min Act: -0.0000

Data Index: 435481 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.6057. Min Act: -0.0000

Data Index: 411359 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.8482. Min Range: -1.8482

Max Act: 1.4948. Min Act: -0.0000

Data Index: 234384 (C4 (Web Text))

Max Activating Token Index: 95