Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2365 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.9581. Min Act: -0.0001

Data Index: 1142130 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.8095. Min Act: -0.0001

Data Index: 483192 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.7872. Min Act: -0.0001

Data Index: 637011 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.4516. Min Act: -0.0001

Data Index: 284068 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.5019. Min Act: -0.0001

Data Index: 467692 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.9171. Min Act: -0.0001

Data Index: 751975 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.0355. Min Act: -0.0001

Data Index: 218340 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.2965. Min Act: -0.0001

Data Index: 995917 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.0952. Min Act: -0.0001

Data Index: 1074689 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.0334. Min Act: -0.0001

Data Index: 1349772 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.8962. Min Act: -0.0001

Data Index: 394795 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.9569. Min Act: -0.0001

Data Index: 344197 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.8937. Min Act: -0.0001

Data Index: 876190 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.8865. Min Act: -0.0001

Data Index: 225292 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.9368. Min Act: -0.0001

Data Index: 350231 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.9688. Min Act: -0.0001

Data Index: 1190980 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.8338. Min Act: -0.0001

Data Index: 850636 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.9581. Min Range: -1.9581

Max Act: 1.0137. Min Act: -0.0001

Data Index: 587844 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.7070. Min Act: -0.0001

Data Index: 903563 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.9581. Min Range: -1.9581

Max Act: 0.9429. Min Act: -0.0001

Data Index: 652901 (C4 (Web Text))

Max Activating Token Index: 73