Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0003

Data Index: 824536 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0691. Min Act: -0.0003

Data Index: 1038622 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0678. Min Act: -0.0003

Data Index: 108610 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1490659 (Python Code)

Max Activating Token Index: 598

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1379453 (Python Code)

Max Activating Token Index: 984

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0625. Min Act: -0.0003

Data Index: 120486 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0631. Min Act: -0.0003

Data Index: 950302 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0631. Min Act: -0.0003

Data Index: 956450 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0615. Min Act: -0.0003

Data Index: 719297 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1288315 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0611. Min Act: -0.0003

Data Index: 1381269 (Python Code)

Max Activating Token Index: 530

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0607. Min Act: -0.0003

Data Index: 963291 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1469391 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0592. Min Act: -0.0003

Data Index: 5495 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1563601 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0592. Min Act: -0.0003

Data Index: 256697 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1109182 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1294712 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0576. Min Act: -0.0003

Data Index: 946502 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0596. Min Act: -0.0003

Data Index: 842958 (C4 (Web Text))

Max Activating Token Index: 61