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

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

Neuron 4720 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1444511 (Python Code)

Max Activating Token Index: 148

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1611769 (Python Code)

Max Activating Token Index: 517

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1486914 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1371008 (Python Code)

Max Activating Token Index: 737

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1620694 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0752. Min Act: -0.0003

Data Index: 1411707 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1492718 (Python Code)

Max Activating Token Index: 486

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1545915 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1492736 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1567297 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1396559 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1448044 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1406280 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1482850 (Python Code)

Max Activating Token Index: 810

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1555657 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1458976 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1587753 (Python Code)

Max Activating Token Index: 375

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1390755 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1430273 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1565408 (Python Code)

Max Activating Token Index: 533