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

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

Neuron 700 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.5942. Min Act: -0.0001

Data Index: 341890 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.5792. Min Act: -0.0001

Data Index: 928484 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.7215. Min Act: -0.0001

Data Index: 707701 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.5828. Min Act: -0.0001

Data Index: 1149664 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.3405. Min Act: -0.0001

Data Index: 432524 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.6001. Min Act: -0.0001

Data Index: 395794 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.1455. Min Act: -0.0001

Data Index: 1122051 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.2097. Min Act: -0.0001

Data Index: 1222833 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.2421. Min Act: -0.0001

Data Index: 1235709 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 1.7215. Min Range: -1.7215

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1062632 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.2649. Min Act: -0.0001

Data Index: 1249357 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.4625. Min Act: -0.0001

Data Index: 978508 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.0125. Min Act: -0.0001

Data Index: 896635 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.2990. Min Act: -0.0001

Data Index: 1540689 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.0242. Min Act: -0.0001

Data Index: 319337 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.1363. Min Act: -0.0001

Data Index: 1464187 (Python Code)

Max Activating Token Index: 868

Text #16

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.0975. Min Act: -0.0001

Data Index: 261717 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.0886. Min Act: -0.0001

Data Index: 182930 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.1073. Min Act: -0.0001

Data Index: 1147576 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 1.7215. Min Range: -1.7215

Max Act: 1.1015. Min Act: -0.0001

Data Index: 1508068 (Python Code)

Max Activating Token Index: 371