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

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

Neuron 1557 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1595074 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0675. Min Act: -0.0001

Data Index: 422524 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1573647 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1368573 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1570390 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1550984 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1526048 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0621. Min Act: -0.0001

Data Index: 206867 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0693. Min Act: -0.0001

Data Index: 344824 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1372016 (Python Code)

Max Activating Token Index: 739

Text #10

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0626. Min Act: -0.0001

Data Index: 706930 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0640. Min Act: -0.0001

Data Index: 919848 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1306843 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1554069 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0601. Min Act: -0.0001

Data Index: 898848 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1389897 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0576. Min Act: -0.0001

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0597. Min Act: -0.0001

Data Index: 621894 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1488101 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0593. Min Act: -0.0001

Data Index: 493101 (C4 (Web Text))

Max Activating Token Index: 606