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

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

Neuron 1641 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: 0.7015. Min Range: -0.7015

Max Act: 0.7015. Min Act: -0.0000

Data Index: 386096 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1301659 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1321574 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5364. Min Act: -0.0000

Data Index: 828513 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.5212. Min Act: -0.0000

Data Index: 997264 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1175413 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4560. Min Act: -0.0000

Data Index: 179189 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4722. Min Act: -0.0000

Data Index: 158959 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4799. Min Act: -0.0000

Data Index: 610377 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4368. Min Act: -0.0000

Data Index: 687069 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4536. Min Act: -0.0000

Data Index: 368406 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4515. Min Act: -0.0000

Data Index: 351942 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4179. Min Act: -0.0000

Data Index: 924671 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4144. Min Act: -0.0000

Data Index: 199833 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4247. Min Act: -0.0000

Data Index: 239607 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1110198 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.3720. Min Act: -0.0000

Data Index: 112147 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.4096. Min Act: -0.0000

Data Index: 619910 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1161160 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.7015. Min Range: -0.7015

Max Act: 0.3799. Min Act: -0.0000

Data Index: 200959 (C4 (Web Text))

Max Activating Token Index: 667