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

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

Neuron 1437 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1036119 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3659. Min Act: -0.0000

Data Index: 705362 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3765. Min Act: -0.0000

Data Index: 932055 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1346661 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3265. Min Act: -0.0000

Data Index: 322894 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3044. Min Act: -0.0000

Data Index: 86349 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3108. Min Act: -0.0000

Data Index: 421355 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1127184 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1120107 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2885. Min Act: -0.0000

Data Index: 146667 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1348128 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2343. Min Act: -0.0000

Data Index: 223900 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2584. Min Act: -0.0000

Data Index: 243610 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2825. Min Act: -0.0000

Data Index: 882547 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.3027. Min Act: -0.0000

Data Index: 325943 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1318887 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2758. Min Act: -0.0000

Data Index: 639288 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2621. Min Act: -0.0000

Data Index: 154642 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2907. Min Act: -0.0000

Data Index: 881388 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.5352. Min Range: -0.5352

Max Act: 0.2674. Min Act: -0.0000

Data Index: 271099 (C4 (Web Text))

Max Activating Token Index: 208