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

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

Neuron 2030 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.5454. Min Act: -0.0001

Data Index: 729356 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.1714. Min Act: -0.0001

Data Index: 574523 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.1344. Min Act: -0.0001

Data Index: 689313 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.1379. Min Act: -0.0000

Data Index: 298344 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0695. Min Act: -0.0001

Data Index: 703105 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0356. Min Act: -0.0001

Data Index: 1040509 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0688. Min Act: -0.0001

Data Index: 447411 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0528. Min Act: -0.0001

Data Index: 95428 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0138. Min Act: -0.0001

Data Index: 963234 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9595. Min Act: -0.0001

Data Index: 1327690 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.5454. Min Range: -1.5454

Max Act: 1.0171. Min Act: -0.0001

Data Index: 770644 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9536. Min Act: -0.0001

Data Index: 577510 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9755. Min Act: -0.0001

Data Index: 230993 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9417. Min Act: -0.0001

Data Index: 991674 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9084. Min Act: -0.0000

Data Index: 688498 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9196. Min Act: -0.0001

Data Index: 822030 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9752. Min Act: -0.0001

Data Index: 71020 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9704. Min Act: -0.0001

Data Index: 204706 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9399. Min Act: -0.0001

Data Index: 449863 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.5454. Min Range: -1.5454

Max Act: 0.9681. Min Act: -0.0001

Data Index: 636203 (C4 (Web Text))

Max Activating Token Index: 75