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

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

Neuron 49 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.7449. Min Act: -0.0001

Data Index: 1142425 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5899. Min Act: -0.0001

Data Index: 419242 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.3764. Min Act: -0.0001

Data Index: 769999 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.3316. Min Act: -0.0001

Data Index: 111170 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.3155. Min Act: -0.0001

Data Index: 1195482 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.1053. Min Act: -0.0001

Data Index: 984308 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.3385. Min Act: -0.0001

Data Index: 1241067 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.2007. Min Act: -0.0001

Data Index: 969113 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.0339. Min Act: -0.0001

Data Index: 115623 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8433. Min Act: -0.0001

Data Index: 1226536 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8323. Min Act: -0.0001

Data Index: 441781 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8140. Min Act: -0.0001

Data Index: 1242889 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8064. Min Act: -0.0001

Data Index: 274978 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8895. Min Act: -0.0001

Data Index: 200311 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8754. Min Act: -0.0001

Data Index: 500558 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8155. Min Act: -0.0001

Data Index: 623777 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.9281. Min Act: -0.0001

Data Index: 439198 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.7859. Min Act: -0.0001

Data Index: 532249 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.8473. Min Act: -0.0001

Data Index: 164314 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 3.7449. Min Range: -3.7449

Max Act: 2.7021. Min Act: -0.0001

Data Index: 1016819 (C4 (Web Text))

Max Activating Token Index: 506