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

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

Neuron 4096 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9559. Min Range: -4.9559

Max Act: 4.9226. Min Act: -0.0000

Data Index: 900410 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 4.9559. Min Range: -4.9559

Max Act: 4.8584. Min Act: -0.0000

Data Index: 882415 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 4.9559. Min Range: -4.9559

Max Act: 4.9559. Min Act: -0.0000

Data Index: 332841 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 4.9559. Min Range: -4.9559

Max Act: 4.7510. Min Act: -0.0000

Data Index: 371481 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 4.9559. Min Range: -4.9559

Max Act: 4.7222. Min Act: -0.0000

Data Index: 1086910 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 4.9559. Min Range: -4.9559

Max Act: 4.3215. Min Act: -0.0000

Data Index: 340909 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.9440. Min Act: -0.0000

Data Index: 36198 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.6895. Min Act: -0.0000

Data Index: 272109 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.8016. Min Act: -0.0000

Data Index: 1241349 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.8367. Min Act: -0.0000

Data Index: 786962 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.4030. Min Act: -0.0000

Data Index: 1233294 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.3651. Min Act: -0.0000

Data Index: 580126 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.5458. Min Act: -0.0000

Data Index: 1058604 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.3966. Min Act: -0.0000

Data Index: 105772 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.5155. Min Act: -0.0000

Data Index: 639745 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.4959. Min Act: -0.0000

Data Index: 1182229 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.4765. Min Act: -0.0000

Data Index: 933538 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.4715. Min Act: -0.0000

Data Index: 282757 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.3153. Min Act: -0.0000

Data Index: 324583 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 4.9559. Min Range: -4.9559

Max Act: 3.4427. Min Act: -0.0000

Data Index: 947386 (C4 (Web Text))

Max Activating Token Index: 135