Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1902 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1070683 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1118368 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1123414 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0558. Min Act: -0.0002

Data Index: 687234 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0539. Min Act: -0.0002

Data Index: 211737 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0498. Min Act: -0.0002

Data Index: 520053 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0509. Min Act: -0.0002

Data Index: 247854 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1187109 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1251257 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1338228 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0497. Min Act: -0.0002

Data Index: 459157 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0500. Min Act: -0.0002

Data Index: 373659 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1136782 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0500. Min Act: -0.0002

Data Index: 305123 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0500. Min Act: -0.0002

Data Index: 46966 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0494. Min Act: -0.0002

Data Index: 806411 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0447. Min Act: -0.0002

Data Index: 695567 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0449. Min Act: -0.0001

Data Index: 396801 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0455. Min Act: -0.0002

Data Index: 17437 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0457. Min Act: -0.0002

Data Index: 486223 (C4 (Web Text))

Max Activating Token Index: 994