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

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

Neuron 434 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.9454. Min Act: -0.0000

Data Index: 1506374 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.5547. Min Act: -0.0000

Data Index: 1653567 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.6135. Min Act: -0.0000

Data Index: 1620422 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.8512. Min Act: -0.0000

Data Index: 1440943 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.6754. Min Act: -0.0000

Data Index: 1607196 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.8107. Min Act: -0.0000

Data Index: 1526794 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.9546. Min Act: -0.0000

Data Index: 1512362 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.6856. Min Act: -0.0000

Data Index: 1470149 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.9679. Min Act: -0.0000

Data Index: 1384724 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.5539. Min Act: -0.0000

Data Index: 1522474 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.8370. Min Act: -0.0000

Data Index: 1446278 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.6791. Min Act: -0.0000

Data Index: 1496823 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.5094. Min Act: -0.0000

Data Index: 1628686 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1431923 (Python Code)

Max Activating Token Index: 316

Text #14

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.7760. Min Act: -0.0000

Data Index: 1422872 (Python Code)

Max Activating Token Index: 1021

Text #15

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.4913. Min Act: -0.0000

Data Index: 1579710 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.4786. Min Act: -0.0000

Data Index: 1634162 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.7392. Min Act: -0.0000

Data Index: 1424734 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.7362. Min Act: -0.0000

Data Index: 1475936 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 2.9679. Min Range: -2.9679

Max Act: 2.4637. Min Act: -0.0000

Data Index: 1515518 (Python Code)

Max Activating Token Index: 908