Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3869 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6497. Min Act: -0.0001

Data Index: 571362 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6342. Min Act: -0.0001

Data Index: 985493 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6599. Min Act: -0.0001

Data Index: 930466 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.6636. Min Act: -0.0001

Data Index: 656631 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.5807. Min Act: -0.0001

Data Index: 390918 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4866. Min Act: -0.0001

Data Index: 323382 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4368. Min Act: -0.0001

Data Index: 256987 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4617. Min Act: -0.0001

Data Index: 658275 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4610. Min Act: -0.0001

Data Index: 622118 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4451. Min Act: -0.0001

Data Index: 1279953 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4230. Min Act: -0.0001

Data Index: 282940 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4248. Min Act: -0.0001

Data Index: 575225 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.3951. Min Act: -0.0001

Data Index: 314867 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4256. Min Act: -0.0001

Data Index: 473573 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1143535 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4126. Min Act: -0.0001

Data Index: 712981 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.3793. Min Act: -0.0001

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4072. Min Act: -0.0001

Data Index: 340591 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4234. Min Act: -0.0001

Data Index: 354623 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.6636. Min Range: -0.6636

Max Act: 0.4187. Min Act: -0.0001

Data Index: 91563 (C4 (Web Text))

Max Activating Token Index: 879