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

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

Neuron 4151 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0043. Min Act: -0.0000

Data Index: 125641 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0776. Min Act: -0.0000

Data Index: 910534 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0800. Min Act: -0.0000

Data Index: 940595 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1101584 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0586. Min Act: -0.0000

Data Index: 673687 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.0800. Min Range: -1.0800

Max Act: 1.0084. Min Act: -0.0000

Data Index: 893971 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8733. Min Act: -0.0000

Data Index: 657829 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9805. Min Act: -0.0000

Data Index: 154070 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1323156 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.9296. Min Act: -0.0000

Data Index: 151889 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1069177 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8147. Min Act: -0.0000

Data Index: 921822 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8672. Min Act: -0.0000

Data Index: 795813 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8113. Min Act: -0.0000

Data Index: 877715 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8022. Min Act: -0.0000

Data Index: 430277 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.8272. Min Act: -0.0000

Data Index: 3861 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.7882. Min Act: -0.0000

Data Index: 247976 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1353255 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.7553. Min Act: -0.0000

Data Index: 52232 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.0800. Min Range: -1.0800

Max Act: 0.7737. Min Act: -0.0000

Data Index: 935565 (C4 (Web Text))

Max Activating Token Index: 569