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

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

Neuron 3105 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6667. Min Act: -0.0001

Data Index: 1649784 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6234. Min Act: -0.0001

Data Index: 1556902 (Python Code)

Max Activating Token Index: 310

Text #2

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6104. Min Act: -0.0001

Data Index: 1588376 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1615631 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1444925 (Python Code)

Max Activating Token Index: 874

Text #5

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6015. Min Act: -0.0001

Data Index: 1563203 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6115. Min Act: -0.0001

Data Index: 1440524 (Python Code)

Max Activating Token Index: 572

Text #7

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6254. Min Act: -0.0001

Data Index: 1422975 (Python Code)

Max Activating Token Index: 474

Text #8

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.6073. Min Act: -0.0001

Data Index: 1601932 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5859. Min Act: -0.0001

Data Index: 1562057 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5768. Min Act: -0.0001

Data Index: 1439514 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5677. Min Act: -0.0001

Data Index: 1393164 (Python Code)

Max Activating Token Index: 704

Text #12

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5578. Min Act: -0.0001

Data Index: 1479607 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5822. Min Act: -0.0001

Data Index: 1492206 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5532. Min Act: -0.0001

Data Index: 1504924 (Python Code)

Max Activating Token Index: 497

Text #15

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1552163 (Python Code)

Max Activating Token Index: 454

Text #16

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5201. Min Act: -0.0001

Data Index: 1652486 (Python Code)

Max Activating Token Index: 625

Text #17

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.4743. Min Act: -0.0001

Data Index: 1417550 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1407687 (Python Code)

Max Activating Token Index: 688

Text #19

Max Range: 0.6765. Min Range: -0.6765

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1442558 (Python Code)

Max Activating Token Index: 400