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

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

Neuron 4318 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0002

Data Index: 858543 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 738007 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 139668 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0024. Min Act: -0.0002

Data Index: 342593 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 653682 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 910970 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 201548 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 911416 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1127211 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 703216 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 992754 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 13655 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1214530 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 933945 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1492708 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0002

Data Index: 100689 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0022. Min Act: -0.0002

Data Index: 76260 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0002

Data Index: 391690 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0002

Data Index: 383716 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1424839 (Python Code)

Max Activating Token Index: 392