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

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

Neuron 3427 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: 0.6021. Min Range: -0.6021

Max Act: 0.6021. Min Act: -0.0000

Data Index: 504474 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5396. Min Act: -0.0000

Data Index: 293626 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5167. Min Act: -0.0000

Data Index: 306863 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.5090. Min Act: -0.0000

Data Index: 258424 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4844. Min Act: 0.0000

Data Index: 613580 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4834. Min Act: -0.0000

Data Index: 716761 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4774. Min Act: -0.0000

Data Index: 242765 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4967. Min Act: -0.0000

Data Index: 535845 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4620. Min Act: -0.0000

Data Index: 468016 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4575. Min Act: -0.0000

Data Index: 532954 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4518. Min Act: -0.0000

Data Index: 29244 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4058. Min Act: -0.0000

Data Index: 536108 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4155. Min Act: -0.0000

Data Index: 208590 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4200. Min Act: -0.0000

Data Index: 23020 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1316808 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3981. Min Act: -0.0000

Data Index: 716199 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3714. Min Act: -0.0000

Data Index: 421399 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3797. Min Act: -0.0000

Data Index: 113773 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.3917. Min Act: -0.0000

Data Index: 337482 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.6021. Min Range: -0.6021

Max Act: 0.4131. Min Act: -0.0000

Data Index: 482781 (C4 (Web Text))

Max Activating Token Index: 909