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

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

Neuron 2578 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.7571. Min Act: -0.0000

Data Index: 375911 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6283. Min Act: -0.0000

Data Index: 371967 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6146. Min Act: -0.0000

Data Index: 69567 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.6188. Min Act: -0.0000

Data Index: 578918 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5889. Min Act: -0.0000

Data Index: 791862 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5905. Min Act: -0.0000

Data Index: 732793 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5652. Min Act: -0.0000

Data Index: 805127 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5695. Min Act: -0.0000

Data Index: 489810 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1106156 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1205477 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5810. Min Act: -0.0000

Data Index: 270651 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.4919. Min Act: -0.0000

Data Index: 831901 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5374. Min Act: -0.0000

Data Index: 277736 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5234. Min Act: -0.0000

Data Index: 700643 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5543. Min Act: -0.0000

Data Index: 970717 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5589. Min Act: -0.0000

Data Index: 415167 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5357. Min Act: -0.0000

Data Index: 316524 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5233. Min Act: -0.0000

Data Index: 356569 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5495. Min Act: -0.0000

Data Index: 768111 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.7571. Min Range: -0.7571

Max Act: 0.5370. Min Act: -0.0000

Data Index: 463863 (C4 (Web Text))

Max Activating Token Index: 665