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

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

Neuron 1516 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: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0000

Data Index: 439781 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4929. Min Act: -0.0000

Data Index: 657430 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4659. Min Act: -0.0000

Data Index: 324249 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4397. Min Act: -0.0000

Data Index: 229179 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4079. Min Act: -0.0000

Data Index: 70768 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1068213 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4200. Min Act: -0.0000

Data Index: 981081 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4005. Min Act: -0.0000

Data Index: 210166 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4304. Min Act: -0.0000

Data Index: 264886 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3806. Min Act: -0.0000

Data Index: 645813 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1276229 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3582. Min Act: -0.0000

Data Index: 682738 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3529. Min Act: -0.0000

Data Index: 890009 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3755. Min Act: -0.0000

Data Index: 896640 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3544. Min Act: -0.0000

Data Index: 618187 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3389. Min Act: -0.0000

Data Index: 963354 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3807. Min Act: -0.0000

Data Index: 869835 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3421. Min Act: -0.0000

Data Index: 442048 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3611. Min Act: -0.0000

Data Index: 375315 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.3682. Min Act: -0.0000

Data Index: 476014 (C4 (Web Text))

Max Activating Token Index: 155