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

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

Neuron 98 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: 0.9661. Min Range: -0.9661

Max Act: 0.8990. Min Act: -0.0000

Data Index: 206873 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.9624. Min Act: -0.0000

Data Index: 207745 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.9661. Min Act: -0.0000

Data Index: 75808 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1096768 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.8724. Min Act: -0.0000

Data Index: 591349 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.8785. Min Act: -0.0000

Data Index: 298058 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1203471 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1235142 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1127005 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.5328. Min Act: -0.0000

Data Index: 224943 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6692. Min Act: -0.0000

Data Index: 339086 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.7024. Min Act: -0.0000

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6558. Min Act: -0.0000

Data Index: 859113 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6887. Min Act: -0.0000

Data Index: 498225 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.7386. Min Act: -0.0000

Data Index: 31342 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6664. Min Act: 0.0001

Data Index: 450739 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6536. Min Act: -0.0000

Data Index: 448535 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6732. Min Act: -0.0000

Data Index: 167580 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.6061. Min Act: -0.0000

Data Index: 205548 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.9661. Min Range: -0.9661

Max Act: 0.5801. Min Act: -0.0000

Data Index: 42496 (C4 (Web Text))

Max Activating Token Index: 550