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

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

Neuron 1870 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0670. Min Act: -0.0003

Data Index: 814330 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1051112 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1178835 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1064032 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0548. Min Act: -0.0002

Data Index: 613563 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0449. Min Act: -0.0003

Data Index: 894152 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0496. Min Act: -0.0003

Data Index: 301725 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0444. Min Act: -0.0003

Data Index: 416320 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0501. Min Act: -0.0003

Data Index: 331239 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0440. Min Act: -0.0002

Data Index: 691080 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0471. Min Act: -0.0002

Data Index: 966783 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0450. Min Act: -0.0003

Data Index: 974800 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0472. Min Act: -0.0003

Data Index: 860136 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0467. Min Act: -0.0002

Data Index: 555754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0427. Min Act: -0.0003

Data Index: 559483 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0393. Min Act: -0.0003

Data Index: 616336 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1253963 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1353717 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0436. Min Act: -0.0002

Data Index: 55226 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0430. Min Act: -0.0003

Data Index: 273725 (C4 (Web Text))

Max Activating Token Index: 602