Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2327 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6569. Min Act: -0.0001

Data Index: 332246 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.6007. Min Act: -0.0001

Data Index: 316613 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5395. Min Act: -0.0001

Data Index: 838568 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5183. Min Act: -0.0001

Data Index: 259145 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5051. Min Act: -0.0001

Data Index: 901813 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4768. Min Act: -0.0001

Data Index: 64726 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.5074. Min Act: -0.0001

Data Index: 1007297 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4552. Min Act: -0.0001

Data Index: 1092018 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4730. Min Act: -0.0001

Data Index: 574701 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4676. Min Act: -0.0001

Data Index: 674087 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4709. Min Act: -0.0001

Data Index: 597151 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4411. Min Act: -0.0001

Data Index: 642697 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4617. Min Act: -0.0001

Data Index: 1149073 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4597. Min Act: -0.0001

Data Index: 867848 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4365. Min Act: -0.0001

Data Index: 1060714 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4598. Min Act: -0.0001

Data Index: 611678 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1252540 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4416. Min Act: -0.0001

Data Index: 381398 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4715. Min Act: -0.0001

Data Index: 290009 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.6569. Min Range: -0.6569

Max Act: 0.4437. Min Act: -0.0001

Data Index: 461917 (C4 (Web Text))

Max Activating Token Index: 892