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

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

Neuron 2625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3743. Min Act: -0.0000

Data Index: 598736 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1138891 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1177894 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3592. Min Act: -0.0000

Data Index: 797806 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1156754 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3368. Min Act: -0.0000

Data Index: 618614 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1613302 (Python Code)

Max Activating Token Index: 330

Text #7

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1471564 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2795. Min Act: -0.0000

Data Index: 132311 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2769. Min Act: -0.0000

Data Index: 240585 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1370103 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2675. Min Act: -0.0000

Data Index: 195439 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1531025 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1109462 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2571. Min Act: -0.0000

Data Index: 124221 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1348007 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1192384 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2455. Min Act: -0.0000

Data Index: 724434 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1438696 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 0.3811. Min Range: -0.3811

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1214674 (C4 (Web Text))

Max Activating Token Index: 449