Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3406 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1021234 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7417. Min Act: -0.0000

Data Index: 129425 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1126636 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7134. Min Act: -0.0000

Data Index: 9904 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7183. Min Act: -0.0000

Data Index: 859572 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7129. Min Act: -0.0000

Data Index: 972828 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1261464 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6199. Min Act: -0.0000

Data Index: 265224 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6450. Min Act: -0.0000

Data Index: 632332 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6955. Min Act: -0.0000

Data Index: 223224 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6455. Min Act: -0.0000

Data Index: 331775 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5762. Min Act: -0.0000

Data Index: 818935 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5400. Min Act: -0.0000

Data Index: 545130 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6252. Min Act: -0.0000

Data Index: 854243 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6081. Min Act: -0.0000

Data Index: 445791 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5437. Min Act: -0.0000

Data Index: 967765 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1056750 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5607. Min Act: -0.0000

Data Index: 114017 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5295. Min Act: -0.0000

Data Index: 869520 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5967. Min Act: -0.0000

Data Index: 177873 (C4 (Web Text))

Max Activating Token Index: 213