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

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

Neuron 3528 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: 1.2837. Min Range: -1.2837

Max Act: 1.2837. Min Act: -0.0000

Data Index: 191505 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0847. Min Act: -0.0000

Data Index: 30011 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1174845 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1083535 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9774. Min Act: -0.0000

Data Index: 366087 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0398. Min Act: -0.0000

Data Index: 30831 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1102829 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9879. Min Act: -0.0000

Data Index: 789357 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9669. Min Act: -0.0000

Data Index: 386126 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1298570 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8490. Min Act: -0.0000

Data Index: 685625 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8219. Min Act: -0.0000

Data Index: 86528 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8255. Min Act: -0.0000

Data Index: 578659 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8946. Min Act: -0.0000

Data Index: 705837 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8126. Min Act: -0.0000

Data Index: 732518 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8351. Min Act: -0.0000

Data Index: 578858 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8241. Min Act: -0.0000

Data Index: 889216 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8371. Min Act: -0.0000

Data Index: 357337 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.7833. Min Act: -0.0000

Data Index: 78618 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1183766 (C4 (Web Text))

Max Activating Token Index: 362