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

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

Neuron 2774 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0761. Min Act: -0.0003

Data Index: 1370895 (Python Code)

Max Activating Token Index: 822

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1609788 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1446654 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1415507 (Python Code)

Max Activating Token Index: 798

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1393894 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0648. Min Act: -0.0003

Data Index: 1651294 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1574920 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1548638 (Python Code)

Max Activating Token Index: 852

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1619635 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1538806 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0685. Min Act: -0.0003

Data Index: 1395571 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1416880 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0650. Min Act: -0.0004

Data Index: 1457214 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1437947 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0653. Min Act: -0.0004

Data Index: 1576311 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1575978 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1652230 (Python Code)

Max Activating Token Index: 841

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1490675 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1465281 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1525076 (Python Code)

Max Activating Token Index: 835