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

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

Neuron 414 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.2028. Min Act: -0.0001

Data Index: 724137 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1965. Min Act: -0.0001

Data Index: 558425 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1933. Min Act: -0.0002

Data Index: 108473 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.2003. Min Act: -0.0001

Data Index: 189445 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1788. Min Act: -0.0002

Data Index: 60261 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1890. Min Act: -0.0002

Data Index: 140225 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1810. Min Act: -0.0001

Data Index: 768739 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1112014 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1813. Min Act: -0.0001

Data Index: 161175 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1762. Min Act: -0.0001

Data Index: 126220 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1615. Min Act: -0.0001

Data Index: 123943 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1665. Min Act: -0.0001

Data Index: 710994 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1710. Min Act: -0.0002

Data Index: 133857 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1777. Min Act: -0.0002

Data Index: 1177014 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1695. Min Act: -0.0001

Data Index: 860656 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1637. Min Act: -0.0002

Data Index: 431046 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1687. Min Act: -0.0002

Data Index: 1003980 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1564. Min Act: -0.0001

Data Index: 56574 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1792. Min Act: -0.0001

Data Index: 881333 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.2028. Min Range: -0.2028

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1312667 (C4 (Web Text))

Max Activating Token Index: 145