Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0005

Data Index: 964332 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1103. Min Act: -0.0005

Data Index: 712642 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0889. Min Act: -0.0005

Data Index: 341491 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0910. Min Act: -0.0005

Data Index: 777955 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0853. Min Act: -0.0005

Data Index: 228340 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0889. Min Act: -0.0005

Data Index: 275269 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0862. Min Act: -0.0005

Data Index: 428195 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0827. Min Act: -0.0005

Data Index: 268204 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0867. Min Act: -0.0005

Data Index: 729254 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0801. Min Act: -0.0005

Data Index: 460014 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0767. Min Act: -0.0005

Data Index: 285176 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0793. Min Act: -0.0005

Data Index: 257422 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0787. Min Act: -0.0005

Data Index: 403692 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0804. Min Act: -0.0005

Data Index: 837004 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0784. Min Act: -0.0005

Data Index: 643779 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0784. Min Act: -0.0005

Data Index: 714367 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0777. Min Act: -0.0005

Data Index: 626745 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0764. Min Act: -0.0005

Data Index: 378687 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0770. Min Act: -0.0005

Data Index: 1173132 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0793. Min Act: -0.0005

Data Index: 127592 (C4 (Web Text))

Max Activating Token Index: 688