Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4023. Min Range: -2.4023

Max Act: 2.4023. Min Act: -0.0000

Data Index: 759493 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 2.4023. Min Range: -2.4023

Max Act: 2.3291. Min Act: -0.0000

Data Index: 120059 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.4023. Min Range: -2.4023

Max Act: 2.2048. Min Act: -0.0000

Data Index: 1010453 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 2.4023. Min Range: -2.4023

Max Act: 2.0813. Min Act: -0.0000

Data Index: 160034 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 2.4023. Min Range: -2.4023

Max Act: 2.0445. Min Act: -0.0000

Data Index: 744722 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.9840. Min Act: -0.0000

Data Index: 1209210 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.9895. Min Act: -0.0000

Data Index: 1044451 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1157331 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.9156. Min Act: -0.0000

Data Index: 247221 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.8280. Min Act: -0.0000

Data Index: 1285075 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.8893. Min Act: -0.0000

Data Index: 843920 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.8822. Min Act: -0.0000

Data Index: 688156 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1219650 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.7428. Min Act: -0.0000

Data Index: 1231318 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.7125. Min Act: -0.0000

Data Index: 274524 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.7040. Min Act: -0.0000

Data Index: 217175 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.8029. Min Act: -0.0000

Data Index: 681173 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1175553 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.7697. Min Act: -0.0000

Data Index: 378099 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.4023. Min Range: -2.4023

Max Act: 1.6535. Min Act: -0.0000

Data Index: 349289 (C4 (Web Text))

Max Activating Token Index: 847