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

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

Neuron 1820 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0490. Min Act: -0.0001

Data Index: 509518 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8565. Min Act: -0.0000

Data Index: 512868 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7852. Min Act: -0.0000

Data Index: 843685 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7323. Min Act: -0.0000

Data Index: 412870 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7769. Min Act: -0.0000

Data Index: 737118 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7413. Min Act: -0.0001

Data Index: 838790 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7261. Min Act: -0.0001

Data Index: 280725 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6812. Min Act: -0.0000

Data Index: 267876 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6890. Min Act: -0.0000

Data Index: 99116 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1214475 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6795. Min Act: -0.0001

Data Index: 1049956 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1054866 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1101171 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6857. Min Act: -0.0000

Data Index: 767485 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.5989. Min Act: -0.0000

Data Index: 906739 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1051551 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.5958. Min Act: -0.0001

Data Index: 1175409 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6523. Min Act: -0.0000

Data Index: 760261 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1147904 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6275. Min Act: -0.0000

Data Index: 96198 (C4 (Web Text))

Max Activating Token Index: 216