Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 849 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1373741 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1462983 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0275. Min Act: -0.0000

Data Index: 1612686 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1442202 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1500090 (Python Code)

Max Activating Token Index: 717

Text #5

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1464036 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1588050 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1508067 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0776. Min Act: -0.0000

Data Index: 1461608 (Python Code)

Max Activating Token Index: 511

Text #9

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0123. Min Act: -0.0000

Data Index: 1654093 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0186. Min Act: -0.0001

Data Index: 1605640 (Python Code)

Max Activating Token Index: 677

Text #11

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1446403 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1505009 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1424634 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 1.1588. Min Range: -1.1588

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1646853 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1449117 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1408608 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1479612 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1589078 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 1.1588. Min Range: -1.1588

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1594187 (Python Code)

Max Activating Token Index: 602