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

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

Neuron 1171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3397. Min Act: -0.0002

Data Index: 282894 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3129. Min Act: -0.0002

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3160. Min Act: -0.0002

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3234. Min Act: -0.0002

Data Index: 372888 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2839. Min Act: -0.0002

Data Index: 1133375 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2880. Min Act: -0.0002

Data Index: 795115 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.3047. Min Act: -0.0002

Data Index: 82333 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2953. Min Act: -0.0002

Data Index: 643249 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2841. Min Act: -0.0002

Data Index: 79422 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2933. Min Act: -0.0002

Data Index: 915813 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2622. Min Act: -0.0002

Data Index: 412227 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2652. Min Act: -0.0002

Data Index: 568539 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2590. Min Act: -0.0002

Data Index: 1353530 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2397. Min Act: -0.0002

Data Index: 102312 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2544. Min Act: -0.0002

Data Index: 1332714 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2506. Min Act: -0.0002

Data Index: 870149 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2379. Min Act: -0.0002

Data Index: 894935 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2297. Min Act: -0.0002

Data Index: 199316 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2500. Min Act: -0.0002

Data Index: 797029 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.3397. Min Range: -0.3397

Max Act: 0.2508. Min Act: -0.0002

Data Index: 435837 (C4 (Web Text))

Max Activating Token Index: 80