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

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

Neuron 4498 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.1186. Min Act: -0.0000

Data Index: 864626 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1083357 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9536. Min Act: -0.0001

Data Index: 237863 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8540. Min Act: -0.0000

Data Index: 821638 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9781. Min Act: -0.0000

Data Index: 714907 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1176071 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9149. Min Act: -0.0000

Data Index: 312381 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9110. Min Act: -0.0000

Data Index: 825368 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9252. Min Act: -0.0000

Data Index: 801498 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9833. Min Act: -0.0000

Data Index: 341469 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8113. Min Act: -0.0000

Data Index: 437935 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9365. Min Act: -0.0001

Data Index: 1047740 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8770. Min Act: -0.0000

Data Index: 558846 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8354. Min Act: -0.0000

Data Index: 45060 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8232. Min Act: -0.0000

Data Index: 410603 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8950. Min Act: -0.0000

Data Index: 337704 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1307762 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9008. Min Act: -0.0001

Data Index: 148175 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.7583. Min Act: -0.0000

Data Index: 438991 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1113929 (C4 (Web Text))

Max Activating Token Index: 186