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

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

Neuron 4406 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: 2.2898. Min Range: -2.2898

Max Act: 2.2898. Min Act: -0.0000

Data Index: 1120322 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8368. Min Act: -0.0000

Data Index: 1199364 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9455. Min Act: -0.0000

Data Index: 287049 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.0744. Min Act: -0.0000

Data Index: 487273 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9313. Min Act: -0.0000

Data Index: 1263825 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 2.2898. Min Range: -2.2898

Max Act: 2.0098. Min Act: -0.0000

Data Index: 393211 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9516. Min Act: -0.0000

Data Index: 876873 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8615. Min Act: -0.0000

Data Index: 306724 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9377. Min Act: -0.0000

Data Index: 1146280 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7858. Min Act: -0.0000

Data Index: 1124311 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8563. Min Act: -0.0000

Data Index: 228008 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7469. Min Act: -0.0000

Data Index: 39858 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.9361. Min Act: -0.0000

Data Index: 347267 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7614. Min Act: -0.0000

Data Index: 520072 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7249. Min Act: -0.0000

Data Index: 658218 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8560. Min Act: -0.0000

Data Index: 1129659 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.5870. Min Act: -0.0000

Data Index: 1301721 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8464. Min Act: -0.0000

Data Index: 129732 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.8204. Min Act: -0.0000

Data Index: 637955 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 2.2898. Min Range: -2.2898

Max Act: 1.7135. Min Act: -0.0000

Data Index: 790783 (C4 (Web Text))

Max Activating Token Index: 457