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

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

Neuron 768 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1487621 (Python Code)

Max Activating Token Index: 157

Text #1

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1586016 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1450881 (Python Code)

Max Activating Token Index: 497

Text #3

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1373713 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1504728 (Python Code)

Max Activating Token Index: 769

Text #5

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1530476 (Python Code)

Max Activating Token Index: 290

Text #6

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1459149 (Python Code)

Max Activating Token Index: 512

Text #7

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1538312 (Python Code)

Max Activating Token Index: 887

Text #8

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1557932 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1540010 (Python Code)

Max Activating Token Index: 610

Text #10

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1270698 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1278760 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1578371 (Python Code)

Max Activating Token Index: 600

Text #13

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1467430 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1529480 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5140. Min Act: -0.0000

Data Index: 302696 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1468686 (Python Code)

Max Activating Token Index: 122

Text #17

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1555998 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1218396 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1570886 (Python Code)

Max Activating Token Index: 855