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

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

Neuron 557 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: 0.3471. Min Range: -0.3471

Max Act: 0.3321. Min Act: -0.0000

Data Index: 925474 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3471. Min Act: -0.0000

Data Index: 451925 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3233. Min Act: -0.0000

Data Index: 460228 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.3003. Min Act: -0.0000

Data Index: 145107 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1106638 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2918. Min Act: -0.0000

Data Index: 621080 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1182575 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1134836 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2928. Min Act: -0.0000

Data Index: 448829 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2830. Min Act: -0.0000

Data Index: 760292 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1324619 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2708. Min Act: -0.0000

Data Index: 182912 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2436. Min Act: -0.0000

Data Index: 460837 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2758. Min Act: -0.0000

Data Index: 823915 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1348441 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1247521 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2513. Min Act: -0.0000

Data Index: 548612 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1325140 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2751. Min Act: -0.0000

Data Index: 666908 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.3471. Min Range: -0.3471

Max Act: 0.2442. Min Act: -0.0000

Data Index: 275690 (C4 (Web Text))

Max Activating Token Index: 955